ring%3adev-cycle（环%3adev 循环）

Development Cycle Orchestrator

Standards Loading (MANDATORY)

Before any gate execution, you MUST load Ring standards:

<fetch_required> https://raw.githubusercontent.com/LerianStudio/ring/main/CLAUDE.md </fetch_required>

Fetch URL above and extract: Agent Modification Verification requirements, Anti-Rationalization Tables requirements, and Critical Rules.

<block_condition>

• WebFetch fails or returns empty
• CLAUDE.md not accessible </block_condition>

If any condition is true, STOP and report blocker. Cannot proceed without Ring standards.

Overview

The development cycle orchestrator loads tasks/subtasks from PM team output (or manual task files) and executes through 10 gates (Gate 0–9) at three cadences (subtask / task / cycle). Gate 0 includes delivery verification as an inline exit check. Deferred execution applies for infrastructure-dependent tests:

• Gates 0-5, 8-9 (per unit): Write code + run tests per task/subtask
• Gates 6-7 (per unit): Write/update integration and chaos test code, verify compilation, but do not execute tests (no containers)
• Gates 6-7 (end of cycle): Execute all integration and chaos tests once after all units complete

This keeps test code current with each feature while avoiding redundant container spin-ups during development.

MUST announce at start: "I'm using the ring:dev-cycle skill to orchestrate task execution through 10 gates (Gate 0–9). Subtask-level: 0 (implementation + delivery verification exit check), 3 (unit testing), 9 (validation). Task-level (after all subtasks): 1 (devops), 2 (SRE), 4 (fuzz), 5 (property), 6 write (integration), 7 write (chaos), 8 (review — 10 reviewers). Cycle-end: gates 6/7 execute mode, multi-tenant verify, dev-report, final commit."

⛔ CRITICAL: Specialized Agents Perform All Tasks

See shared-patterns/shared-orchestrator-principle.md for full ORCHESTRATOR principle, role separation, forbidden/required actions, gate-to-agent mapping, and anti-rationalization table.

Summary: You orchestrate. Agents execute. If using Read/Write/Edit/Bash on source code → STOP. Dispatch agent.

⛔ ORCHESTRATOR BOUNDARIES (HARD GATE)

This section defines exactly what the orchestrator CAN and CANNOT do.

What Orchestrator CAN Do (PERMITTED)

What Orchestrator CANNOT Do (FORBIDDEN)

Any of these actions by orchestrator = IMMEDIATE VIOLATION. Dispatch agent instead.

The 3-FILE RULE

If a task requires editing MORE than 3 files → MUST dispatch specialist agent.

This is not negotiable:

• 1-3 files of non-source content (markdown, json, yaml) → Orchestrator MAY edit directly
• 1+ source code files (*.go, *.ts, *.tsx) → MUST dispatch agent
• 4+ files of any type → MUST dispatch agent

Orchestrator Workflow Order (MANDATORY)

┌─────────────────────────────────────────────────────────────────┐
│  CORRECT WORKFLOW ORDER                                         │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  1. Load task file (Read docs/pre-dev/*/tasks.md or docs/ring:dev-refactor/*/tasks.md) │
│  2. Ask execution mode (AskUserQuestion)                        │
│  3. Determine state path + Check/Load state (see State Path Selection) │
│  4. WebFetch Ring Standards                                     │
│  5. ⛔ LOAD SUB-SKILL for current gate (Skill tool)            │
│  6. Execute sub-skill instructions (dispatch agent via Task)    │
│  7. Wait for agent completion                                   │
│  8. Verify agent output (Standards Coverage Table)              │
│  9. Update state (Write to JSON)                               │
│  10. Proceed to next gate                                       │
│                                                                 │
│  ════════════════════════════════════════════════════════════   │
│  ❌ WRONG: Load → Mode → Standards → Task(agent) directly       │
│  ✅ RIGHT: Load → Mode → Standards → Skill(sub) → Task(agent)   │
│  ════════════════════════════════════════════════════════════   │
└─────────────────────────────────────────────────────────────────┘

⛔ SUB-SKILL LOADING IS MANDATORY (HARD GATE)

Before dispatching any agent, you MUST load the corresponding sub-skill first.

<cannot_skip>

• Gate 0: Skill("ring:dev-implementation") → then Task(subagent_type="ring:backend-engineer-*",...). Gate 0 includes delivery verification exit check inline (a sub-check of ring:dev-implementation Step 7): verifies all requirements are DELIVERED (not just created), catches dead code, unwired structs, unregistered middleware, and runs 7 automated checks: (A) file size ≤1000 lines soft / ≤1500 hard (cohesion review for 1001-1500), (B) license headers, (C) linting, (D) migration safety, (E) vulnerability scanning, (F) API backward compatibility, (G) multi-tenant dual-mode. FAIL → ring:dev-implementation re-iterates with fix instructions.
• Gate 1: Skill("ring:dev-devops") → then Task(subagent_type="ring:devops-engineer",...)
• Gate 2: Skill("ring:dev-sre") → then Task(subagent_type="ring:sre",...)
• Gate 3: Skill("ring:dev-unit-testing") → then Task(subagent_type="ring:qa-analyst", test_mode="unit",...)
• Gate 4: Skill("ring:dev-fuzz-testing") → then Task(subagent_type="ring:qa-analyst", test_mode="fuzz",...)
• Gate 5: Skill("ring:dev-property-testing") → then Task(subagent_type="ring:qa-analyst", test_mode="property",...)
• Gate 6: Skill("ring:dev-integration-testing") → per unit: write/update tests + compile check (no execution); end of cycle: execute
• Gate 7: Skill("ring:dev-chaos-testing") → per unit: write/update tests + compile check (no execution); end of cycle: execute
• Gate 8: Skill("ring:codereview") → then 5x Task(...) in parallel
• Gate 9: Skill("ring:dev-validation") → N/A (verification only) </cannot_skip>

Between "WebFetch standards" and "Task(agent)" there MUST be "Skill(sub-skill)".

The workflow for each gate is:

1. Skill("[sub-skill-name]")     ← Load sub-skill instructions
2. Follow sub-skill instructions  ← Sub-skill tells you HOW to dispatch
3. Task(subagent_type=...)       ← Dispatch agent as sub-skill instructs
4. Validate agent output          ← Per sub-skill validation rules
5. Update state                   ← Record results

Custom Instructions (Optional Second Argument)

Validation: See shared-patterns/custom-prompt-validation.md for max length (500 chars), sanitization rules, gate protection, and conflict handling.

If custom_prompt is set in state, inject it into ALL agent dispatches:

Task tool:
  subagent_type: "ring:backend-engineer-golang"
  prompt: |
    **CUSTOM CONTEXT (from user):**
    {state.custom_prompt}

    ---

    **Standard Instructions:**
    [... rest of agent prompt ...]

Rules for custom prompt:

1. Inject at TOP of prompt - User context takes precedence
2. Preserve in state - custom_prompt persists for resume
3. Include in execution report - Document what context was used
4. Forward via state - Sub-skills read custom_prompt from state file and inject into their agent dispatches (no explicit parameter passing needed)

Example custom prompts and their effect:

Anti-Rationalization for Skipping Sub-Skills

Between "WebFetch standards" and "Task(agent)" there MUST be "Skill(sub-skill)".

Anti-Rationalization for Direct Coding

Red Flags - Orchestrator Violation in Progress

If you catch yourself doing any of these, STOP IMMEDIATELY:

🚨 RED FLAG: About to Read *.go or *.ts file
   → STOP. Dispatch agent instead.

🚨 RED FLAG: About to Write/Create source code
   → STOP. Dispatch agent instead.

🚨 RED FLAG: About to Edit source code
   → STOP. Dispatch agent instead.

🚨 RED FLAG: About to run "go test" or "npm test"
   → STOP. Agent runs tests, not you.

🚨 RED FLAG: Thinking "I'll just..."
   → STOP. "Just" is the warning word. Dispatch agent.

🚨 RED FLAG: Thinking "This is simple enough..."
   → STOP. Simplicity is irrelevant. Dispatch agent.

🚨 RED FLAG: Standards loaded, but next action is not Task tool
   → STOP. After standards, IMMEDIATELY dispatch agent.

Recovery from Orchestrator Violation

If you violated orchestrator boundaries:

1. STOP current execution immediately
2. DISCARD any direct changes (git checkout --.)
3. DISPATCH the correct specialist agent
4. Agent implements from scratch following TDD
5. Document the violation for feedback loop

Sunk cost of direct work is IRRELEVANT. Agent dispatch is MANDATORY.

Blocker Criteria - STOP and Report

<block_condition>

• Gate Failure: Tests not passing, review failed → STOP, cannot proceed to next gate
• Missing Standards: No PROJECT_RULES.md → STOP, report blocker and wait
• Agent Failure: Specialist agent returned errors → STOP, diagnose and report
• User Decision Required: Architecture choice, framework selection → STOP, present options </block_condition>

You CANNOT proceed when blocked. Report and wait for resolution.

Cannot Be Overridden

<cannot_skip>

• All 10 gates must execute across their respective cadences: Subtask loop (Gate 0 → 3 → 9), then Task-level (Gate 1 → 2 → 4 → 5 → 6 write → 7 write → 8), then Cycle-end (Gate 6 execute → 7 execute → multi-tenant verify → dev-report → final commit).
• Gate 0 includes delivery verification exit check inline (MUST NOT dispatch a separate gate for delivery verification).
• All testing gates (3-7) are MANDATORY - Comprehensive test coverage ensures quality
• Gate 8 requires all 10 reviewers - Different review perspectives are complementary
• Coverage threshold ≥ 85% - Industry standard for quality code
• PROJECT_RULES.md must exist - Cannot verify standards without target </cannot_skip>

No exceptions. User cannot override. Time pressure cannot override.

Severity Calibration

Report all severities. Let user prioritize.

Reviewer Verdicts Are Final

MEDIUM issues found in Gate 4 MUST be fixed. No exceptions.

Severity mapping is absolute:

• CRITICAL/HIGH/MEDIUM → Fix NOW, re-run all 10 reviewers
• LOW → Add TODO(review): comment
• Cosmetic → Add FIXME(nitpick): comment

No negotiation. No exceptions. No "special cases".

Pressure Resistance

See shared-patterns/shared-pressure-resistance.md for universal pressure scenarios.

Gate-specific note: Execution mode selection affects CHECKPOINTS (user approval pauses), not GATES (quality checks). all gates execute regardless of mode.

Common Rationalizations - REJECTED

See shared-patterns/shared-anti-rationalization.md for universal anti-rationalizations.

Gate-specific rationalizations:

Red Flags - STOP

See shared-patterns/shared-red-flags.md for universal red flags.

If you catch yourself thinking any of those patterns, STOP immediately and return to gate execution.

Incremental Compromise Prevention

The "just this once" pattern leads to complete gate erosion:

Day 1: "Skip review just this once" → Approved (precedent set)
Day 2: "Skip testing, we did it last time" → Approved (precedent extended)
Day 3: "Skip implementation checks, pattern established" → Approved (gates meaningless)
Day 4: Production incident from Day 1 code

Prevention rules:

1. No incremental exceptions - Each exception becomes the new baseline
2. Document every pressure - Log who requested, why, outcome
3. Escalate patterns - If same pressure repeats, escalate to team lead
4. Gates are binary - Complete or incomplete. No "mostly done".

Gate Completion Definition (HARD GATE)

A gate is COMPLETE only when all components finish successfully:

CRITICAL for Gate 8: Running 9 of 10 reviewers is not a partial pass - it's a FAIL. Re-run all 10 reviewers.

Anti-Rationalization for Partial Gates:

Gate Order Enforcement (HARD GATE)

Gates MUST execute in this order within each task:

1. Subtask loop (per subtask OR per task-itself if no subtasks):

- Gate 0 (Implementation — INCLUDES delivery verification exit check inline) - Gate 3 (Unit Testing) - Gate 9 (Validation)

1. After all subtasks complete their subtask-level gates — task-level gates (once per task):

- Gate 1 (DevOps) - Gate 2 (SRE) - Gate 4 (Fuzz) - Gate 5 (Property) - Gate 6 (Integration — write mode) - Gate 7 (Chaos — write mode) - Gate 8 (Review — 10 reviewers)

1. End of cycle (once per cycle):

- Gate 6 (Integration — execute mode) - Gate 7 (Chaos — execute mode) - Multi-Tenant Verify (Step 12.0.5, Gate 0.5G reconciliation) - Gate 0.5D — Migration Safety Verification (Step 12.0.5b, conditional on SQL migration files in cycle diff) - dev-report (aggregate) - Final Commit

Deferred Execution Model for Gates 6-7:

• Write mode (task-level): Write/update test code + verify compilation (no container execution)
• Execute mode (end of cycle): Execute all integration and chaos tests (containers spun up once), then verify multi-tenant dual-mode compliance (already implemented at Gate 0, verified at Gate 0.5G)

All testing gates (3-7) are MANDATORY. No exceptions. No skip reasons.

Gates are not parallelizable across different gates. Sequential execution is MANDATORY within each cadence layer.

The 10 Gates

All gates are MANDATORY. No exceptions. No skip reasons.

Note: Gate 0 includes delivery verification exit criteria. See Step 2.3.1.

Gates 6-7 Deferred Execution: Test code is written/updated per unit to stay current. Actual test execution (with containers) happens once at end of cycle.

Integrated PM → Dev Workflow

PM Team Output → Dev Team Execution (/ring:dev-cycle)

Execution Order

Core Principle (two-level cadence):

• Subtask-level gates run per execution unit (subtask, or task-itself if no subtasks): Gate 0 (Implementation, incl. delivery verification exit check), Gate 3 (Unit Testing), Gate 9 (Validation).
• Task-level gates run ONCE per task, after all its subtasks finish their subtask-level gates: Gate 1 (DevOps), Gate 2 (SRE), Gate 4 (Fuzz), Gate 5 (Property), Gate 6 write (Integration), Gate 7 write (Chaos), Gate 8 (Review — 10 reviewers on cumulative task diff).
• Cycle-level gates run ONCE per cycle, after all tasks are done: Gate 6 execute, Gate 7 execute, Multi-Tenant Verify (Gate 0.5G reconciliation), Gate 0.5D Migration Safety Verification (conditional on SQL migration files), ring:dev-report (aggregate), Final Commit.

Per-Subtask Flow: Subtask → Gate 0 (incl. delivery verification exit check) → Gate 3 → Gate 9 → [opt-in subtask visual report] → [subtask checkpoint if execution_mode = manual_per_subtask] Per-Task Flow (after all subtasks done): Gate 1 → Gate 2 → Gate 4 → Gate 5 → Gate 6 (write) → Gate 7 (write) → Gate 8 (Review) → Task-level visual report → Accumulate metrics → [task checkpoint if execution_mode in {manual_per_task, manual_per_subtask}] End-of-Cycle Flow: All tasks done → Gate 6 (execute) → Gate 7 (execute) → Multi-Tenant Verify (Step 12.0.5) → Gate 0.5D Migration Safety (Step 12.0.5b, conditional) → ring:dev-report (ONE dispatch, reads accumulated_metrics) → Final Commit

Why deferred execution for Gates 6-7:

• Integration tests require testcontainers (slow to spin up/tear down)
• Chaos tests require Toxiproxy infrastructure
• Running containers per subtask is wasteful when subsequent subtasks modify the same code
• Test code stays current (written per task), infrastructure cost is paid once

Execution Loop Structure (cadence model)

for each task in state.tasks:
  # ===== SUBTASK-LEVEL GATES =====
  for each subtask in task.subtasks (or task-itself if no subtasks):
    Execute Gate 0 (Implementation, includes delivery verification exit check)
    Execute Gate 3 (Unit Testing)
    Execute Gate 9 (Validation)
    [per-subtask visual report — OPT-IN only via state.visual_report_granularity == "subtask"]
    [subtask checkpoint if execution_mode == manual_per_subtask]
  end for

  # ===== TASK-LEVEL GATES =====
  # Input aggregation: implementation_files = UNION across all subtasks of this task.
  # gate0_handoffs = ARRAY of per-subtask implementation handoffs (one per subtask).
  Execute Gate 1 (DevOps)
  Execute Gate 2 (SRE)
  Execute Gate 4 (Fuzz)
  Execute Gate 5 (Property)
  Execute Gate 6 (Integration — write mode)
  Execute Gate 7 (Chaos — write mode)
  Execute Gate 8 (Review — 10 parallel reviewers on cumulative task diff)

  Generate task-level visual report
  Accumulate metrics into state.tasks[i].accumulated_metrics  (no dev-report dispatch here)
  [task checkpoint if execution_mode in {manual_per_task, manual_per_subtask}]
end for

# ===== CYCLE-LEVEL GATES =====
Execute Gate 6 (Integration — execute mode)
Execute Gate 7 (Chaos — execute mode)
Execute Multi-Tenant Verify
Dispatch ring:dev-report (ONE AND ONLY dispatch per cycle — reads accumulated_metrics)
Execute Final Commit

⛔ CADENCE RULE: Gates 1, 2, 4, 5, 6w, 7w, 8 MUST NOT be dispatched during the subtask loop. They are task-cadence — wait until ALL subtasks of the current task have completed Gates 0, 3, and 9 before dispatching them.

Why task-level cadence for Gates 1, 2, 4, 5, 6w, 7w, 8:

• DevOps / SRE / Fuzz / Property: Container configs, observability, edge-case coverage, and invariants are coherent at the task boundary, not at each subtask. Running them per subtask duplicates work against an in-flight feature.
• Integration / Chaos (write): Test scenarios span multiple subtasks; writing them once per task avoids churn as later subtasks land.
• Review (Gate 8): Cumulative task diff shows ALL subtasks' changes at once. Cross-subtask interactions (contract drift, hidden coupling) are MORE visible at this cadence, not less.

Subtask failure semantics: If any subtask's Gate 0, Gate 3, or Gate 9 fails terminally (after retry budget exhausted), the task MUST enter status: failed. Task-cadence gates (1, 2, 4, 5, 6w, 7w, 8) MUST NOT dispatch. Remaining subtasks in that task MUST NOT execute. Cycle halts at the checkpoint for user decision (abort / fix-and-retry / skip-task).

Commit Timing

User selects when commits happen (Step 7 of initialization).

Commit Message Format

Commit Timing vs Execution Mode

Note: Checkpoints (user approval pauses) are controlled by execution_mode. Commits are controlled by commit_timing. They are independent settings.

State Management

State Path Selection (MANDATORY)

The state file path depends on the source of tasks:

Detection Logic:

if source_file contains "docs/ring:dev-refactor/" THEN
  state_path = "docs/ring:dev-refactor/current-cycle.json"
else
  state_path = "docs/ring:dev-cycle/current-cycle.json"

Store state_path in the state object itself so resume knows where to look.

State File Structure

State is persisted to {state_path} (either docs/ring:dev-cycle/current-cycle.json or docs/ring:dev-refactor/current-cycle.json):

{
  "version": "1.1.0",
  "cycle_id": "uuid",
  "started_at": "ISO timestamp",
  "updated_at": "ISO timestamp",
  "source_file": "path/to/tasks.md",
  "state_path": "docs/ring:dev-cycle/current-cycle.json | docs/ring:dev-refactor/current-cycle.json",
  "cycle_type": "feature | refactor",
  "execution_mode": "manual_per_subtask|manual_per_task|automatic",
  "commit_timing": "per_subtask|per_task|at_end",
  "_comment_cached_standards": "Populated by Step 1.5 (Standards Pre-Cache). Dictionary of URL → {fetched_at, content}. Sub-skills MUST read from here instead of calling WebFetch.",
  "cached_standards": {},
  "_comment_visual_report_granularity": "Default 'task' (generate visual report once per task). Opt-in 'subtask' to generate per-subtask reports.",
  "visual_report_granularity": "task",
  "custom_prompt": {
    "type": "string",
    "optional": true,
    "max_length": 500,
    "description": "User-provided context for agents (from second positional argument). Max 500 characters. Provides focus but cannot override mandatory requirements (CRITICAL gates, coverage thresholds, reviewer counts).",
    "validation": "Max 500 chars (truncated with warning if exceeded); whitespace trimmed; control chars stripped (except newlines). Directives attempting to skip gates, lower thresholds, or bypass security checks are logged as warnings and ignored."
  },
  "status": "in_progress|completed|failed|paused|paused_for_approval|paused_for_testing|paused_for_task_approval|paused_for_integration_testing",
  "feedback_loop_completed": false,
  "current_task_index": 0,
  "current_gate": 0,
  "current_subtask_index": 0,
  "_comment_migration_safety_verification": "Populated at Step 12.0.5b (Gate 0.5D — Migration Safety, conditional on SQL migration files present in cycle diff vs origin/main). Cycle-cadence (runs once per cycle, not per task/subtask). status transitions: pending → skipped (no migration files) | completed (no BLOCKING findings) | blocked (BLOCKING unacknowledged) | acknowledged (ACKNOWLEDGE findings approved by user). See Step 12.0.5b state persistence block for full shape.",
  "gate_progress": {
    "migration_safety_verification": {
      "status": "pending|completed|skipped|blocked|acknowledged",
      "files_checked": [],
      "findings": {
        "BLOCKING": 0,
        "WARN": 0,
        "ACKNOWLEDGE": 0
      },
      "user_acknowledgment": null,
      "started_at": null,
      "completed_at": null
    }
  },
  "tasks": [
    {
      "id": "T-001",
      "title": "Task title",
      "status": "pending|in_progress|completed|failed|blocked",
      "feedback_loop_completed": false,
      "_comment_accumulated_metrics": "Populated at Step 11.2 (Task Approval Checkpoint). Aggregated at cycle end by ring:dev-report (Step 12.1).",
      "accumulated_metrics": {
        "gate_durations_ms": {},
        "review_iterations": 0,
        "testing_iterations": 0,
        "issues_by_severity": {
          "CRITICAL": 0,
          "HIGH": 0,
          "MEDIUM": 0,
          "LOW": 0
        }
      },
      "_comment_subtask_gate_progress": "Subtask-level gate_progress holds SUBTASK-CADENCE gates only: implementation (Gate 0), unit_testing (Gate 3), validation (Gate 9). Task-cadence gates (1, 2, 4, 5, 6w, 7w, 8) live in task.gate_progress, not here.",
      "subtasks": [
        {
          "id": "ST-001-01",
          "file": "subtasks/T-001/ST-001-01.md",
          "status": "pending|completed",
          "gate_progress": {
            "implementation": {
              "status": "pending|in_progress|completed",
              "started_at": "ISO timestamp",
              "tdd_red": {
                "status": "pending|in_progress|completed",
                "test_file": "path/to/test_file.go",
                "failure_output": "FAIL: TestFoo - expected X got nil",
                "completed_at": "ISO timestamp"
              },
              "tdd_green": {
                "status": "pending|in_progress|completed",
                "implementation_file": "path/to/impl.go",
                "test_pass_output": "PASS: TestFoo (0.003s)",
                "completed_at": "ISO timestamp"
              },
              "delivery_verified": false,
              "files_changed": []
            },
            "unit_testing": {
              "status": "pending|in_progress|completed",
              "coverage_actual": 0.0,
              "coverage_threshold": 85
            },
            "validation": {
              "status": "pending|in_progress|completed",
              "result": "pending|approved|rejected"
            }
          }
        }
      ],
      "_comment_task_gate_progress": "Task-level gate_progress holds TASK-CADENCE gates only: devops (1), sre (2), fuzz_testing (4), property_testing (5), integration_testing (6w), chaos_testing (7w), review (8). Subtask-cadence gates (0, 3, 9) live in each subtask's gate_progress, not here. Gates 6/7 keep write_mode and execute_mode phases; execute_mode transitions at cycle end (Step 12.1).",
      "gate_progress": {
        "devops": {"status": "pending"},
        "sre": {"status": "pending"},
        "fuzz_testing": {"status": "pending"},
        "property_testing": {"status": "pending"},
        "integration_testing": {
          "write_mode": {
            "status": "pending|in_progress|completed",
            "test_files": [],
            "compilation_passed": false
          },
          "execute_mode": "pending|completed",
          "scenarios_tested": 0,
          "tests_passed": 0,
          "tests_failed": 0,
          "flaky_tests_detected": 0
        },
        "chaos_testing": {
          "write_mode": {
            "status": "pending|in_progress|completed",
            "test_files": [],
            "compilation_passed": false
          },
          "execute_mode": "pending|completed"
        },
        "review": {"status": "pending"}
      },
      "artifacts": {},
      "agent_outputs": {
        "implementation": {
          "agent": "ring:backend-engineer-golang",
          "output": "## Summary\n...",
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "iterations": 1,
          "standards_compliance": {
            "total_sections": 15,
            "compliant": 14,
            "not_applicable": 1,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "devops": {
          "agent": "ring:devops-engineer",
          "output": "## Summary\n...",
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "iterations": 1,
          "artifacts_created": ["Dockerfile", "docker-compose.yml", ".env.example"],
          "verification_errors": [],
          "standards_compliance": {
            "total_sections": 8,
            "compliant": 8,
            "not_applicable": 0,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "sre": {
          "agent": "ring:sre",
          "output": "## Summary\n...",
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "iterations": 1,
          "instrumentation_coverage": "92%",
          "validation_errors": [],
          "standards_compliance": {
            "total_sections": 10,
            "compliant": 10,
            "not_applicable": 0,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "unit_testing": {
          "agent": "ring:qa-analyst",
          "test_mode": "unit",
          "output": "## Summary\n...",
          "verdict": "PASS",
          "coverage_actual": 87.5,
          "coverage_threshold": 85,
          "iterations": 1,
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "failures": [],
          "uncovered_criteria": [],
          "standards_compliance": {
            "total_sections": 6,
            "compliant": 6,
            "not_applicable": 0,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "fuzz_testing": {
          "agent": "ring:qa-analyst",
          "test_mode": "fuzz",
          "output": "## Summary\n...",
          "verdict": "PASS",
          "corpus_entries": 5,
          "iterations": 1,
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "standards_compliance": {
            "total_sections": 5,
            "compliant": 5,
            "not_applicable": 0,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "property_testing": {
          "agent": "ring:qa-analyst",
          "test_mode": "property",
          "output": "## Summary\n...",
          "verdict": "PASS",
          "properties_tested": 3,
          "iterations": 1,
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "standards_compliance": {
            "total_sections": 5,
            "compliant": 5,
            "not_applicable": 0,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "integration_testing": {
          "agent": "ring:qa-analyst",
          "test_mode": "integration",
          "output": "## Summary\n...",
          "verdict": "PASS",
          "scenarios_tested": 5,
          "tests_passed": 5,
          "tests_failed": 0,
          "flaky_tests_detected": 0,
          "iterations": 1,
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "standards_compliance": {
            "total_sections": 10,
            "compliant": 10,
            "not_applicable": 0,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "chaos_testing": {
          "agent": "ring:qa-analyst",
          "test_mode": "chaos",
          "output": "## Summary\n...",
          "verdict": "PASS",
          "failure_scenarios_tested": 4,
          "recovery_verified": true,
          "iterations": 1,
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "standards_compliance": {
            "total_sections": 5,
            "compliant": 5,
            "not_applicable": 0,
            "non_compliant": 0,
            "gaps": []
          }
        },
        "review": {
          "iterations": 1,
          "timestamp": "ISO timestamp",
          "duration_ms": 0,
          "code_reviewer": {
            "agent": "ring:code-reviewer",
            "output": "...",
            "verdict": "PASS",
            "timestamp": "...",
            "issues": [],
            "standards_compliance": {
              "total_sections": 12,
              "compliant": 12,
              "not_applicable": 0,
              "non_compliant": 0,
              "gaps": []
            }
          },
          "business_logic_reviewer": {
            "agent": "ring:business-logic-reviewer",
            "output": "...",
            "verdict": "PASS",
            "timestamp": "...",
            "issues": [],
            "standards_compliance": {
              "total_sections": 8,
              "compliant": 8,
              "not_applicable": 0,
              "non_compliant": 0,
              "gaps": []
            }
          },
          "security_reviewer": {
            "agent": "ring:security-reviewer",
            "output": "...",
            "verdict": "PASS",
            "timestamp": "...",
            "issues": [],
            "standards_compliance": {
              "total_sections": 10,
              "compliant": 10,
              "not_applicable": 0,
              "non_compliant": 0,
              "gaps": []
            }
          }
        },
        "validation": {
          "result": "approved|rejected",
          "timestamp": "ISO timestamp"
        }
      }
    }
  ],
  "metrics": {
    "total_duration_ms": 0,
    "gate_durations": {},
    "review_iterations": 0,
    "testing_iterations": 0
  }
}

Structured Error/Issue Schemas

These schemas enable ring:dev-report to analyze issues without parsing raw output.

Standards Compliance Gap Schema

{
  "section": "Error Handling (MANDATORY)",
  "status": "❌",
  "reason": "Missing error wrapping with context",
  "file": "internal/handler/user.go",
  "line": 45,
  "evidence": "return err // should wrap with additional context"
}

Test Failure Schema

{
  "test_name": "TestUserCreate_InvalidEmail",
  "test_file": "internal/handler/user_test.go",
  "error_type": "assertion",
  "expected": "ErrInvalidEmail",
  "actual": "nil",
  "message": "Expected validation error for invalid email format",
  "stack_trace": "user_test.go:42 → user.go:28"
}

Review Issue Schema

{
  "severity": "MEDIUM",
  "category": "error-handling",
  "description": "Error not wrapped with context before returning",
  "file": "internal/handler/user.go",
  "line": 45,
  "suggestion": "Use fmt.Errorf(\"failed to create user: %w\", err)",
  "fixed": false,
  "fixed_in_iteration": null
}

DevOps Verification Error Schema

{
  "check": "docker_build",
  "status": "FAIL",
  "error": "COPY failed: file not found in build context: go.sum",
  "suggestion": "Ensure go.sum exists and is not in .dockerignore"
}

SRE Validation Error Schema

{
  "check": "structured_logging",
  "status": "FAIL",
  "file": "internal/handler/user.go",
  "line": 32,
  "error": "Using fmt.Printf instead of structured logger",
  "suggestion": "Use logger.Info().Str(\"user_id\", id).Msg(\"user created\")"
}

Populating Structured Data

Each gate MUST populate its structured fields when saving to state:

All gates track standards_compliance:

• total_sections: Count from agent's standards file (via standards-coverage-table.md)
• compliant: Sections marked ✅ in Standards Coverage Table
• not_applicable: Sections marked N/A
• non_compliant: Sections marked ❌ (MUST be 0 to pass gate)
• gaps[]: Detailed info for each ❌ section (even if later fixed)

Empty arrays [] indicate no issues found - this is valid data for feedback-loop.

⛔ State Persistence Rule (MANDATORY)

"Update state" means BOTH update the object and write to file. Not just in-memory.

After every Gate Transition

You MUST execute these steps after completing any gate (0, 1, 2, 3, 4, or 5):

# Step 1: Update state object with gate results
state.tasks[current_task_index].gate_progress.[gate_name].status = "completed"
state.tasks[current_task_index].gate_progress.[gate_name].completed_at = "[ISO timestamp]"
state.current_gate = [next_gate_number]
state.updated_at = "[ISO timestamp]"

# Step 2: Write to file (MANDATORY - use Write tool)
Write tool:
  file_path: [state.state_path]  # Use state_path from state object
  content: [full JSON state]

State Persistence Checkpoints

⛔ Cadence-aware write paths. Subtask-level gates (0, 3, 9) write to state.tasks[i].subtasks[j].gate_progress.<gate_name>. Task-level gates (1, 2, 4, 5, 6w, 7w, 8) write to state.tasks[i].gate_progress.<gate_name>. Never write task-level gate status under a subtask and never write subtask-level gate status under the task.

tasks.md Status update rules (apply at the three checkpoints above):

If state.source_file is absent or file does not exist → log warning "tasks.md Status updates skipped: source_file missing" and skip all status updates for this cycle.

task_id = state.tasks[state.current_task_index].id
# Always the parent TASK ID — do NOT use current_subtask_index
# Rows where column 1 is "TOTAL" or empty → skip, not a task row

Use Edit tool on state.source_file (tasks.md):
- Find the row starting with `| {task_id} |` in the `## Summary` table
- Before Gate 0: replace `⏸️ Pending` with `🔄 Doing`
  - If already `🔄 Doing` (resumed cycle) → skip, no change needed
- Step 11.2 (all subtasks done, user approved): replace `🔄 Doing` with `✅ Done`
- HARD BLOCK (any gate, task abandoned): replace `🔄 Doing` with `❌ Failed`
  - If row shows `⏸️ Pending` (unexpected) → replace with target value anyway
- If row not found or no Status column → log warning "Status update skipped: task {task_id} row not found in {source_file}" and continue, do not abort

Anti-Rationalization for State Persistence

Step 0: Verify PROJECT_RULES.md Exists (HARD GATE)

NON-NEGOTIABLE. Cycle CANNOT proceed without project standards.

Step 0 Flow

┌─────────────────────────────────────────────────────────────────────────────┐
│  Check: Does docs/PROJECT_RULES.md exist?                                   │
│                                                                             │
│  ├── YES → Proceed to Step 1 (Initialize or Resume)                        │
│  │                                                                          │
│  └── no → ASK: "Is this a LEGACY project (created without PM workflow)?"   │
│       │                                                                     │
│       ├── YES (legacy project) → LEGACY PROJECT ANALYSIS:                   │
│       │   Step 1: Dispatch ring:codebase-explorer (technical info only)          │
│       │   Step 2: Ask 3 questions (what agent can't determine):             │
│       │     1. What do you need help with?                                  │
│       │     2. Any external APIs not visible in code?                       │
│       │     3. Any specific technology not in Ring Standards?               │
│       │   Step 3: Generate PROJECT_RULES.md (deduplicated from Ring)        │
│       │   Note: Business rules belong in PRD, not in PROJECT_RULES          │
│       │   → Proceed to Step 1                                               │
│       │                                                                     │
│       └── no (new project) → ASK: "Do you have PRD, TRD, or Feature Map?"  │
│           │                                                                 │
│           ├── YES (has PM docs) → "Please provide the file path(s)"        │
│           │   → Read PRD/TRD/Feature Map → Extract info                    │
│           │   → Generate PROJECT_RULES.md                                  │
│           │   → Ask supplementary questions if info is incomplete          │
│           │   → Save and proceed to Step 1                                 │
│           │                                                                 │
│           └── no (no PM docs) → ⛔ HARD BLOCK:                              │
│               "PM documents are REQUIRED for new projects.                  │
│                Run /ring:pre-dev-full or /ring:pre-dev-feature first."               │
│               → STOP (cycle cannot proceed)                                 │
└─────────────────────────────────────────────────────────────────────────────┘

Step 0.1: Check for PROJECT_RULES.md

# Check if file exists
Read tool:
  file_path: "docs/PROJECT_RULES.md"

# If file exists and has content → Proceed to Step 1
# If file does not exist or is empty → Continue to Step 0.2

Step 0.2: Check if Legacy Project

Ask the User

Use AskUserQuestion:

┌─────────────────────────────────────────────────────────────────┐
│ 📋 PROJECT_RULES.md not FOUND                                   │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│ I need to create docs/PROJECT_RULES.md to understand your       │
│ project's specific conventions and domain.                      │
│                                                                 │
│ First, I need to know: Is this a LEGACY project?                │
│                                                                 │
│ A legacy project is one that was created WITHOUT using the      │
│ PM team workflow (no PRD, TRD, or Feature Map documents).       │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Question

"Is this a legacy project (created without PM team workflow)?"

Options

(a) Yes, this is a legacy project (b) No, this is a new project following Ring workflow

If YES (legacy)

Go to Step 0.2.1 (Legacy Project Analysis)

If no (new project)

Go to Step 0.3 (Check for PM Documents)

Step 0.2.1: Legacy Project Analysis (Technical Only)

Overview

For legacy projects, analyze codebase for TECHNICAL information only:

┌─────────────────────────────────────────────────────────────────┐
│ 📋 LEGACY PROJECT ANALYSIS                                      │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│ Since this is a legacy project, I'll analyze the codebase       │
│ for TECHNICAL information (not business rules).                 │
│                                                                 │
│ Step 1: Automated analysis (ring:codebase-explorer)                  │
│ Step 2: Ask for project-specific tech not in Ring Standards     │
│ Step 3: Generate PROJECT_RULES.md (deduplicated)                │
│                                                                 │
│ Note: Business rules belong in PRD/product docs, not here.      │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Step 0.2.1a: Automated Codebase Analysis (MANDATORY)

⛔ You MUST use the Task tool to dispatch ring:codebase-explorer. This is not implicit.

Dispatch Agent

Dispatch ring:codebase-explorer to analyze the legacy project for TECHNICAL information:

Action: Use Task tool with EXACTLY these parameters:

┌─────────────────────────────────────────────────────────────────────────────────┐
│  ⛔ If Task tool not used → Analysis does not happen → PROJECT_RULES.md INVALID │
└─────────────────────────────────────────────────────────────────────────────────┘

# Agent 1: Codebase Explorer - Technical Analysis
Task tool:
  subagent_type: "ring:codebase-explorer"
  description: "Analyze legacy project for PROJECT_RULES.md"
  prompt: |
    Analyze this LEGACY codebase to extract technical information for PROJECT_RULES.md.

    This is an existing project created without PM documentation.
    Your job is to understand what exists in the code.

    **Extract:**
    1. **Project Structure:** Directory layout, module organization
    2. **Technical Stack:** Languages, frameworks, databases, external services
    3. **Architecture Patterns:** Clean Architecture, MVC, microservices, etc.
    4. **Existing Features:** Main modules, endpoints, capabilities
    5. **Internal Libraries:** Shared packages, utilities
    6. **Configuration:** Environment variables, config patterns
    7. **Database:** Schema patterns, migrations, ORM usage
    8. **External Integrations:** APIs consumed, message queues

    **Output format:**
    ## Technical Analysis (Legacy Project)

    ### Project Overview
    [What this project appears to do based on code analysis]

    ### Technical Stack
    - Language: [detected]
    - Framework: [detected]
    - Database: [detected]
    - External Services: [detected]

    ### Architecture Patterns
    [Detected patterns]

    ### Existing Features
    [List of features/modules found]

    ### Project Structure
    [Directory layout explanation]

    ### Configuration
    [Env vars, config files found]

    ### External Integrations
    [APIs, services detected]

Note: Business logic analysis is not needed for PROJECT_RULES.md. Business rules belong in PRD/product docs, not technical project rules.

Verification (MANDATORY)

After agent completes, confirm:

• ring:codebase-explorer returned "## Technical Analysis (Legacy Project)" section
• Output contains non-empty content for: Tech Stack, External Integrations, Configuration

If agent failed or returned empty output → Re-dispatch. Cannot proceed without technical analysis.

Step 0.2.1b: Supplementary Questions (Only What Agents Can't Determine)

Post-Analysis Questions

After agents complete, ask only what they couldn't determine from code:

┌─────────────────────────────────────────────────────────────────┐
│ ✓ Codebase Analysis Complete                                    │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│ I've analyzed your codebase. Now I need a few details that      │
│ only you can provide (not visible in the code).                 │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Questions to Ask

Use AskUserQuestion for each:

Note: Business rules belong in PRD/product docs, not in PROJECT_RULES.md.

Step 0.2.1c: Generate PROJECT_RULES.md

Combine Agent Outputs and User Answers

Create tool:
  file_path: "docs/PROJECT_RULES.md"
  content: |
    # Project Rules

    > Ring Standards apply automatically. This file documents only what Ring does not cover.
    > For error handling, logging, testing, architecture, lib-commons → See Ring Standards (auto-loaded by agents)
    > Generated from legacy project analysis.

    ## What Ring Standards Already Cover (DO not ADD HERE)

    The following are defined in Ring Standards and MUST not be duplicated:
    - Error handling patterns (no panic, wrap errors)
    - Logging standards (structured JSON, zerolog/zap)
    - Testing patterns (table-driven tests, mocks)
    - Architecture patterns (Hexagonal, Clean Architecture)
    - Observability (OpenTelemetry, trace correlation)
    - lib-commons usage and patterns
    - API directory structure

    ---

    ## Tech Stack (Not in Ring Standards)

    [From ring:codebase-explorer: Technologies not covered by Ring Standards]
    [e.g., specific message broker, specific cache, DB if not PostgreSQL]

    | Technology | Purpose | Notes |
    |------------|---------|-------|
    | [detected] | [purpose] | [notes] |

    ## Non-Standard Directory Structure

    [From ring:codebase-explorer: Directories that deviate from Ring's standard API structure]
    [e.g., workers/, consumers/, polling/]

    | Directory | Purpose | Pattern |
    |-----------|---------|---------|
    | [detected] | [purpose] | [pattern] |

    ## External Integrations

    [From ring:codebase-explorer: Third-party services specific to this project]

    | Service | Purpose | Docs |
    |---------|---------|------|
    | [detected] | [purpose] | [link] |

    ## Environment Configuration

    [From ring:codebase-explorer: Project-specific env vars not covered by Ring]

    | Variable | Purpose | Example |
    |----------|---------|---------|
    | [detected] | [purpose] | [example] |

    ## Domain Terminology

    [From codebase analysis: Technical names used in this codebase]

    | Term | Definition | Used In |
    |------|------------|---------|
    | [detected] | [definition] | [location] |

    ---

    *Generated: [ISO timestamp]*
    *Source: Legacy project analysis (ring:codebase-explorer)*
    *Ring Standards Version: [version from WebFetch]*

Present to User

┌─────────────────────────────────────────────────────────────────┐
│ ✓ PROJECT_RULES.md Generated for Legacy Project                 │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│ I analyzed your codebase using:                                 │
│   • ring:codebase-explorer (technical patterns, stack, structure)    │
│                                                                 │
│ Combined with your input on:                                    │
│   • Current development goal                                    │
│   • External integrations                                       │
│   • Project-specific technology                                 │
│                                                                 │
│ Generated: docs/PROJECT_RULES.md                                │
│                                                                 │
│ Note: Ring Standards (error handling, logging, testing, etc.)   │
│ are not duplicated - agents load them automatically via WebFetch│
│                                                                 │
│ Please review the file and make any corrections needed.         │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Ask for Approval

Use AskUserQuestion:

• Question: "PROJECT_RULES.md has been generated. Would you like to review it before proceeding?"
• Options: (a) Proceed (b) Open for editing first

After Approval

Proceed to Step 1

Step 0.3: Check for PM Documents (PRD/TRD/Feature Map)

Check for PM Documents

For NEW projects (not legacy), ask about PM documents:

┌─────────────────────────────────────────────────────────────────┐
│ 📋 NEW PROJECT - PM DOCUMENTS CHECK                             │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│ Since this is a new project following Ring workflow, you        │
│ should have PM documents from the pre-dev workflow.             │
│                                                                 │
│ Do you have any of these PM documents?                          │
│   • PRD (Product Requirements Document)                         │
│   • TRD (Technical Requirements Document)                       │
│   • Feature Map (from ring:pre-dev-feature-map skill)                │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Question

"Do you have PRD, TRD, or Feature Map documents for this project?"

Options

(a) Yes, I have PM documents (b) No, I don't have these documents

If YES - Ask for File Paths

"Please provide the file path(s) to your PM documents:
 - PRD path (or 'skip' if none):
 - TRD path (or 'skip' if none):
 - Feature Map path (or 'skip' if none): "

Example Paths

Typical PM team output structure:

docs/pre-dev/{feature-name}/
├── prd.md              → PRD path: docs/pre-dev/auth-system/prd.md
├── trd.md              → TRD path: docs/pre-dev/auth-system/trd.md
├── feature-map.md      → Feature Map path: docs/pre-dev/auth-system/feature-map.md
├── api-design.md
├── data-model.md
└── tasks.md

Common Patterns

• /ring:pre-dev-full output: docs/pre-dev/{feature}/prd.md, trd.md, feature-map.md
• /ring:pre-dev-feature output: docs/pre-dev/{feature}/prd.md, feature-map.md
• Custom locations: User may have docs in different paths (e.g., requirements/, specs/)

Then

Go to Step 0.3.1 (Generate from PM Documents)

If no

HARD BLOCK (Step 0.3.2)

Step 0.3.1: Generate from PM Documents (PRD/TRD/Feature Map)

Read the Provided Documents

# Read PRD if provided
Read tool:
  file_path: "[user-provided PRD path]"

# Read TRD if provided
Read tool:
  file_path: "[user-provided TRD path]"

# Read Feature Map if provided
Read tool:
  file_path: "[user-provided Feature Map path]"

Extract PROJECT_RULES.md Content from PM Documents

⛔ DEDUPLICATION RULE: Extract only what Ring Standards DO NOT cover.

Generate PROJECT_RULES.md

Create tool:
  file_path: "docs/PROJECT_RULES.md"
  content: |
    # Project Rules

    > ⛔ IMPORTANT: Ring Standards are not automatic. Agents MUST WebFetch them before implementation.
    > This file documents only project-specific information not covered by Ring Standards.
    > Generated from PM documents (PRD/TRD/Feature Map).
    >
    > Ring Standards URLs:
    > - Go: https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang.md
    > - TypeScript: https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/typescript.md

    ## What Ring Standards Cover (DO not DUPLICATE HERE)

    The following are defined in Ring Standards and MUST not be duplicated in this file:
    - Error handling patterns (no panic, wrap errors)
    - Logging standards (structured JSON via lib-commons)
    - Testing patterns (table-driven tests, mocks)
    - Architecture patterns (Hexagonal, Clean Architecture)
    - Observability (OpenTelemetry via lib-commons)
    - lib-commons / lib-common-js usage and patterns
    - API directory structure (Lerian pattern)
    - Database connections (PostgreSQL, MongoDB, Redis via lib-commons)
    - Bootstrap pattern (config.go, service.go, server.go)

    **Agents MUST WebFetch Ring Standards and output Standards Coverage Table.**

    ---

    ## Tech Stack (Not in Ring Standards)

    [From TRD/Feature Map: only technologies not covered by Ring Standards]

    | Technology | Purpose | Notes |
    |------------|---------|-------|
    | [detected] | [purpose] | [notes] |

    ## Non-Standard Directory Structure

    [From TRD: Directories that deviate from Ring's standard API structure]

    | Directory | Purpose | Pattern |
    |-----------|---------|---------|
    | [detected] | [purpose] | [pattern] |

    ## External Integrations

    [From TRD/PRD: Third-party services specific to this project]

    | Service | Purpose | Docs |
    |---------|---------|------|
    | [detected] | [purpose] | [link] |

    ## Environment Configuration

    [From TRD: Project-specific env vars not covered by Ring]

    | Variable | Purpose | Example |
    |----------|---------|---------|
    | [detected] | [purpose] | [example] |

    ## Domain Terminology

    [From PRD: Technical names used in this codebase]

    | Term | Definition | Used In |
    |------|------------|---------|
    | [detected] | [definition] | [location] |

    ---

    *Generated from: [PRD path], [TRD path], [Feature Map path]*
    *Ring Standards Version: [version from WebFetch]*
    *Generated: [ISO timestamp]*

Check for Missing Information

If any section is empty or incomplete, ask supplementary questions:

Note: Do not ask about architecture, error handling, logging, testing - Ring Standards covers these.

After Generation

Present to user for review, then proceed to Step 1.

Step 0.3.2: HARD BLOCK - No PM Documents (New Projects Only)

When User Has No PM Documents

┌─────────────────────────────────────────────────────────────────┐
│ ⛔ CANNOT PROCEED - PM DOCUMENTS REQUIRED                       │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│ Development cannot start without PM documents.                  │
│                                                                 │
│ You MUST create PRD, TRD, and/or Feature Map documents first    │
│ using PM team skills:                                           │
│                                                                 │
│   /ring:pre-dev-full     → For features ≥2 days (9 gates)           │
│   /ring:pre-dev-feature  → For features <2 days (4 gates)           │
│                                                                 │
│ These commands will guide you through creating:                 │
│   • PRD (Product Requirements Document)                         │
│   • TRD (Technical Requirements Document)                       │
│   • Feature Map (technology choices, feature relationships)     │
│                                                                 │
│ After completing pre-dev workflow, run /ring:dev-cycle again.        │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Action

STOP EXECUTION. Do not proceed to Step 1.

Step 0 Anti-Rationalization

Pressure Resistance

Step 1: Initialize or Resume

Instructions-Only Mode (no task file)

Input: Custom instructions string without a task file path

Example: /ring:dev-cycle "Add webhook notification support for account status changes"

When custom instructions are provided without a tasks file, ring:dev-cycle generates tasks internally:

1. Detect instructions-only mode: No task file argument AND instructions string provided
2. Analyze prompt: Extract intent, scope, and requirements from the prompt
3. Explore codebase: Dispatch ring:codebase-explorer to understand project structure
4. Generate tasks: Create task structure internally based on prompt + codebase analysis

Task tool:
  subagent_type: "ring:codebase-explorer"
  prompt: |
    Analyze this codebase to support the following implementation request:

    **User Request:** {prompt}

    Provide:
    1. Relevant files and patterns for this request
    2. Suggested task breakdown (T-001, T-002, etc.)
    3. Acceptance criteria for each task
    4. Files that will need modification

    Output as structured task list compatible with ring:dev-cycle.

1. Present generated tasks: Show user the auto-generated task breakdown
2. Confirm with user: "I generated X tasks from your prompt. Proceed?"
3. Set state:

- state_path = "docs/ring:dev-cycle/current-cycle.json" - cycle_type = "prompt" - source_prompt = "[user's prompt]" - Generate tasks array from ring:codebase-explorer output

1. Continue to execution mode selection (Step 1 substeps 7-9)

Anti-Rationalization for Prompt-Only Mode:

New Cycle (with task file path)

Input: path/to/tasks.md or path/to/pre-dev/{feature}/ with optional second argument for custom instructions

Examples:

• /ring:dev-cycle tasks.md
• /ring:dev-cycle tasks.md "Focus on error handling"

1. Detect input: File → Load directly | Directory → Load tasks.md + discover subtasks/
2. Build order: Read tasks, check for subtasks (ST-XXX-01, 02...) or TDD autonomous mode
3. Determine state path:

- if source_file contains docs/ring:dev-refactor/ → state_path = "docs/ring:dev-refactor/current-cycle.json", cycle_type = "refactor" - else → state_path = "docs/ring:dev-cycle/current-cycle.json", cycle_type = "feature"

1. Capture and validate custom instructions: If second argument provided:

- Sanitize input: Trim whitespace, strip control characters (except newlines) - Store validated value: Set custom_prompt field (empty string if not provided) - Note: Directives attempting to skip gates are logged as warnings and ignored at execution time

1. Initialize state: Generate cycle_id, create state file at {state_path}, set indices to 0
2. Display plan: "Loaded X tasks with Y subtasks"
3. ASK EXECUTION MODE (MANDATORY - AskUserQuestion):

- Options: (a) Manual per subtask (b) Manual per task (c) Automatic - Do not skip: User hints ≠ mode selection. Only explicit a/b/c is valid.

1. ASK COMMIT TIMING (MANDATORY - AskUserQuestion):

- Options: (a) Per subtask (b) Per task (c) At the end - Store in commit_timing field in state

1. Start: Display mode + commit timing, proceed to Gate 0

Resume Cycle (--resume flag)

1. Find existing state file:

- Check docs/ring:dev-cycle/current-cycle.json first - If not found, check docs/ring:dev-refactor/current-cycle.json - If neither exists → Error: "No cycle to resume"

1. Load found state file, validate (state_path is stored in the state object)
2. Display: cycle started, tasks completed/total, current task/subtask/gate, paused reason
3. Handle paused states:

Input Validation

Task files are generated by /pre-dev-* or /ring:dev-refactor, which handle content validation. The ring:dev-cycle performs basic format checks:

Format Checks

Step 1.5: Standards Pre-Cache (MANDATORY)

Cache all standards URLs the cycle will need, ONCE, into state.cached_standards. Sub-skills read from this cache instead of calling WebFetch themselves.

Required URLs to pre-fetch (MUST succeed all):

1. https://raw.githubusercontent.com/LerianStudio/ring/main/CLAUDE.md
2. Language-specific (based on detected project stack):

- If Go project: - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/core.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/bootstrap.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/domain.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/domain-modeling.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/api-patterns.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/architecture.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/security.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/quality.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/multi-tenant.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/testing-fuzz.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/testing-property.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/testing-integration.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/testing-chaos.md - If TypeScript backend: - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/typescript.md - https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/typescript/multi-tenant.md

1. https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/devops.md
2. https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/sre.md
3. https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/golang/migration-safety.md (if SQL migrations detected in project)

Protocol:

For each URL in the required list:
  WebFetch: [URL]
  Write to state.cached_standards[URL] = {
    "fetched_at": current_iso_timestamp,
    "content": <fetched content>
  }

MANDATORY: Save state to file after cache populated — Write tool → [state.state_path]

Blocker: If ANY URL fails to fetch, STOP cycle and report. Cache MUST be complete. Sub-skills downstream rely on state.cached_standards being populated; a partial cache causes WebFetch fallback warnings and defeats the purpose of pre-caching.

Rationale: Before this step existed, every sub-skill dispatch triggered its own WebFetch of the same standards. The 5-minute prompt cache TTL is regularly exceeded, producing 15–25+ redundant network fetches per cycle. A single pre-cache at cycle start reduces that to one fetch per unique URL.

Step 1.6: Detect External Dependencies (Cycle-Level Auto-Detection)

MANDATORY: Scan the codebase once at cycle start to detect external dependencies. Store in state.detected_dependencies for use by Gates 2, 6, and 7.

detected_dependencies = []

1. Scan docker-compose.yml / docker-compose.yaml for service images:
   - Grep tool: pattern "postgres" in docker-compose* files → add "postgres"
   - Grep tool: pattern "mongo" in docker-compose* files → add "mongodb"
   - Grep tool: pattern "valkey" in docker-compose* files → add "valkey"
   - Grep tool: pattern "redis" in docker-compose* files → add "redis"
   - Grep tool: pattern "rabbitmq" in docker-compose* files → add "rabbitmq"

2. Scan dependency manifests:
   if language == "go":
     - Grep tool: pattern "github.com/lib/pq" in go.mod → add "postgres"
     - Grep tool: pattern "github.com/jackc/pgx" in go.mod → add "postgres"
     - Grep tool: pattern "go.mongodb.org/mongo-driver" in go.mod → add "mongodb"
     - Grep tool: pattern "github.com/redis/go-redis" in go.mod → add "redis"
     - Grep tool: pattern "github.com/valkey-io/valkey-go" in go.mod → add "valkey"
     - Grep tool: pattern "github.com/rabbitmq/amqp091-go" in go.mod → add "rabbitmq"

   if language == "typescript":
     - Grep tool: pattern "\"pg\"" in package.json → add "postgres"
     - Grep tool: pattern "@prisma/client" in package.json → add "postgres"
     - Grep tool: pattern "\"mongodb\"" in package.json → add "mongodb"
     - Grep tool: pattern "\"mongoose\"" in package.json → add "mongodb"
     - Grep tool: pattern "\"redis\"" in package.json → add "redis"
     - Grep tool: pattern "\"ioredis\"" in package.json → add "redis"
     - Grep tool: pattern "@valkey" in package.json → add "valkey"
     - Grep tool: pattern "\"amqplib\"" in package.json → add "rabbitmq"
     - Grep tool: pattern "amqp-connection-manager" in package.json → add "rabbitmq"

3. Deduplicate detected_dependencies
4. Store: state.detected_dependencies = detected_dependencies
5. Log: "Auto-detected external dependencies: [detected_dependencies]"

### ⛔ MANDATORY: Multi-Tenant Detection & Compliance Audit

<cannot_skip>
MANDATORY: Multi-tenant dual-mode applies to all Go services (no exceptions). Gate 0 implements dual-mode from the start using lib-commons v5 resolvers. Gate 0.5G verifies compliance. This detection captures the CURRENT state of the codebase for context.

See [multi-tenant.md](../../docs/standards/golang/multi-tenant.md) for the canonical model. Verification checks are performed inline by Gate 0.5G (Step 12.0.5) of this skill.
</cannot_skip>

1. Detect existing multi-tenant code and audit compliance:

multi_tenant_exists = false multi_tenant_compliant = false

if language == "go": // Phase 1: Detection - Grep tool: pattern "MULTI_TENANT_ENABLED" in internal/ --include="*.go" → multi_tenant_exists = true - Grep tool: pattern "dispatch layer" in go.mod → multi_tenant_exists = true - Grep tool: pattern "TenantMiddleware\|WithPG\|WithMB" in internal/ --include="*.go" → multi_tenant_exists = true

// Phase 2: Compliance audit (only if multi_tenant_exists = true) if multi_tenant_exists: compliance_checks = {} - Grep: "TENANT_MANAGER_ADDRESS\|TENANT_URL\|TENANT_MANAGER_URL" in internal/ → if match: compliance_checks.config = "NON-COMPLIANT" - Grep: "tmmiddleware.NewTenantMiddleware" in internal/ → if no match: compliance_checks.middleware = "NON-COMPLIANT" - Grep: "tmcore.GetPGContext\|tmcore.GetMBContext" in internal/ → if no match: compliance_checks.repositories = "NON-COMPLIANT" - Grep: "WithCircuitBreaker" in internal/ → if no match: compliance_checks.circuit_breaker = "NON-COMPLIANT" - Grep: "TestMultiTenant_BackwardCompatibility" in internal/ → if no match: compliance_checks.backward_compat = "NON-COMPLIANT"

if all checks pass: multi_tenant_compliant = true else: multi_tenant_compliant = false

if language == "typescript": - Grep tool: pattern "MULTI_TENANT_ENABLED" in src/ --include="*.ts" → multi_tenant_exists = true - Grep tool: pattern "dispatch layer" in package.json → multi_tenant_exists = true // TypeScript compliance audit follows same pattern

state.multi_tenant_exists = multi_tenant_exists state.multi_tenant_compliant = multi_tenant_compliant

if multi_tenant_exists && multi_tenant_compliant: Log: "Multi-tenant COMPLIANT — Gate 0 agent uses dual-mode resolvers, Gate 0.5G will verify" elif multi_tenant_exists && !multi_tenant_compliant: Log: "Multi-tenant DETECTED but NON-COMPLIANT — Gate 0 agent must fix, Gate 0.5G will verify" else: Log: "Multi-tenant NOT detected — Gate 0 agent will implement dual-mode, Gate 0.5G will verify"

**MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]**

<auto_detect_reason> PM team task files often omit external_dependencies. If the codebase uses postgres, mongodb, valkey, or rabbitmq, these MUST be detected and passed to Gates 6 (integration) and 7 (chaos). Auto-detection at cycle level avoids redundant scans per gate.

Multi-tenant state is detected here and passed to Gate 0 (implementation) and Gate 0.5G (verification). See [multi-tenant.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../../docs/standards/golang/multi-tenant.md) for the canonical model and compliance criteria. </auto_detect_reason>

### License Detection (Advisory)

Detect the repository license at cycle start. This check is advisory — it does not block Gate 0. If no license is found, prompt the user; if the user declines, log a warning and proceed.

1. Detect repository license:

license_type = "unknown"

- ls LICENSE LICENSE.md LICENSE.txt 2>/dev/null - If found: - grep -l "Apache License" LICENSE* → license_type = "apache" - grep -l "Elastic License" LICENSE* → license_type = "elv2" - grep -l "All rights reserved.*Lerian" LICENSE* → license_type = "proprietary" - If not found (no LICENSE file): → Ask user: "No LICENSE file detected. Which license should this repository use? [apache|elv2|proprietary|skip]" → If user selects a license: set license_type = <chosen value>, invoke Skill("ring:dev-licensing") with chosen type → If user selects "skip": set license_type = "skip", log "⚠️ WARNING: No LICENSE file. License headers may be inconsistent."

Store: state.license_type = license_type Log: "License detected: {license_type}"

---

## Step 2: Gate 0 - Implementation (Per Execution Unit)

ℹ️ **CADENCE:** Subtask-level. Execution unit is always a subtask (or the task-itself when the task has no subtasks). Writes to `state.tasks[i].subtasks[j].gate_progress.implementation`. Task-level gates (1, 2, 4, 5, 6w, 7w, 8) MUST NOT be dispatched from inside this step — they run after the subtask loop.

**REQUIRED SUB-SKILL:** Use ring:dev-implementation

**Execution Unit:** Task-itself (if no subtasks) or a Subtask (if task has subtasks). Either way, the unit is a SUBTASK-LEVEL scope.

### Pre-Dispatch: Before Gate 0 Checkpoint (MANDATORY)

MUST execute the **Before Gate 0 (task start)** row from the State Persistence Checkpoints table before sub-steps 2.1–2.3:

- Set `task.status = "in_progress"` in state JSON
- Update tasks.md Status → `🔄 Doing` (per tasks.md Status update rules in that table)
- Write state to file

CANNOT proceed to sub-steps 2.1–2.3 without completing this checkpoint.

### ⛔ MANDATORY: Invoke ring:dev-implementation Skill (not inline execution)

See [shared-patterns/shared-orchestrator-principle.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../shared-patterns/shared-orchestrator-principle.md) for full details.

**⛔ FORBIDDEN: Executing TDD-RED/GREEN logic directly from this step.** MUST invoke the ring:dev-implementation skill via the Skill tool; it handles all TDD phases, agent selection, agent dispatch, standards verification, and fix iteration.

### ⛔ Post-Generation Panic Check (MANDATORY)

After ring:dev-implementation completes, verify generated code:

| Check | Command | Expected | If Found |
| --- | --- | --- | --- |
| No panic() | `grep -rn "panic(" --include="*.go" --exclude="*_test.go"` | 0 results | Return to Gate 0 with fix instructions |
| No log.Fatal() | `grep -rn "log.Fatal" --include="*.go"` | 0 results | Return to Gate 0 with fix instructions |
| No Must* helpers | `grep -rn "Must[A-Z]" --include="*.go" \| grep -v "regexp\.MustCompile"` | 0 results | Return to Gate 0 with fix instructions |
| No os.Exit() | `grep -rn "os.Exit" --include="*.go" --exclude="main.go"` | 0 results | Return to Gate 0 with fix instructions |

**If any check fails: DO NOT proceed to Gate 1. Return to Gate 0 with specific fix instructions.**

### ⛔ File Size Enforcement (MANDATORY — All Gates)

See [shared-patterns/file-size-enforcement.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../shared-patterns/file-size-enforcement.md) for thresholds, cohesion judgment, verification commands, split strategies, and agent instructions.

**Summary:** Soft limit 1000 lines per file; hard block at 1500 lines. Files in the 1001-1500 band require cohesion review — keep if coherent (state machine, parser, schema, table-driven tests, tightly-coupled domain logic), split if fragmentable without artificial boundaries. Files > 1500 lines are hard-blocked unless explicit cohesion justification is documented in the PR description. Enforcement points:

- **Gate 0:** Implementation agent receives file-size instructions; orchestrator runs verification command after agent completes. Files 1001-1500 → cohesion review; files > 1500 → hard block.
- **Gate 0 exit check (inline in ring:dev-implementation Step 7):** Delivery verification runs 7 checks as exit criteria: (A) file-size, (B) license headers, (C) linting, (D) migration safety, (E) vulnerability scanning, (F) API backward compatibility, (G) multi-tenant dual-mode. Any FAIL → ring:dev-implementation re-iterates with specific fix instructions.
- **Gate 8:** Code reviewers MUST flag any file > 1000 lines as a MEDIUM+ issue (apply cohesion judgment); files > 1500 lines are CRITICAL.

### Step 2.1: Prepare Input for ring:dev-implementation Skill

Gather from current execution unit:

implementation_input = { // REQUIRED - from current execution unit unit_id: state.current_unit.id, requirements: state.current_unit.acceptance_criteria,

// REQUIRED - detected from project language: state.current_unit.language, // "go" | "typescript" | "python" service_type: state.current_unit.service_type, // "api" | "worker" | "batch" | "cli" | "frontend" | "bff"

// OPTIONAL - additional context technical_design: state.current_unit.technical_design || null, existing_patterns: state.current_unit.existing_patterns || [], project_rules_path: "docs/PROJECT_RULES.md" }

### Step 2.2: Invoke ring:dev-implementation Skill

1. Record gate start timestamp

1. REQUIRED: Invoke ring:dev-implementation skill with structured input:

Skill("ring:dev-implementation") with input: unit_id: implementation_input.unit_id requirements: implementation_input.requirements language: implementation_input.language service_type: implementation_input.service_type technical_design: implementation_input.technical_design existing_patterns: implementation_input.existing_patterns project_rules_path: implementation_input.project_rules_path

The skill handles: - Selecting appropriate agent (Go/TS/Frontend based on language) - TDD-RED phase (writing failing test, capturing failure output) - TDD-GREEN phase (implementing code to pass test) - Standards compliance verification (iteration loop, max 3 attempts) - Re-dispatching agent for compliance fixes - Outputting Standards Coverage Table with evidence

1. REQUIRED: Parse skill output for results:

Expected output sections: - "## Implementation Summary" → status (PASS/FAIL), agent used - "## TDD Results" → RED/GREEN phase status - "## Files Changed" → created/modified files list - "## Handoff to Next Gate" → ready_for_gate_1: YES/NO

if skill output contains "Status: PASS" and "Ready for Gate 1: YES": → Gate 0 PASSED. Proceed to Step 2.3.

if skill output contains "Status: FAIL" or "Ready for Gate 1: NO": → Gate 0 BLOCKED. → Skill already dispatched fixes to implementation agent → Skill already re-ran TDD and standards verification → If "ESCALATION" in output: STOP and report to user

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 2.3: Gate 0 Complete

1. When ring:dev-implementation skill returns PASS:

REQUIRED: Parse from skill output: - agent_used: extract from "## Implementation Summary" - tdd_red_status: extract from "## TDD Results" table - tdd_green_status: extract from "## TDD Results" table - files_changed: extract from "## Files Changed" table - standards_compliance: extract from Standards Coverage Table

- agent_outputs.implementation = { skill: "ring:dev-implementation", agent: "[agent used by skill]", output: "[full skill output]", timestamp: "[ISO timestamp]", duration_ms: [execution time], tdd_red: { status: "completed", test_file: "[from skill output]", failure_output: "[from skill output]" }, tdd_green: { status: "completed", implementation_files: "[from skill output]", pass_output: "[from skill output]" }, standards_compliance: { total_sections: [N from skill output], compliant: [N sections with ✅], not_applicable: [N sections with N/A], non_compliant: 0 } }

1. Display to user:

┌─────────────────────────────────────────────────┐ │ ✓ GATE 0 COMPLETE │ ├─────────────────────────────────────────────────┤ │ Skill: ring:dev-implementation │ │ Agent: [agent_used] │ │ TDD-RED: FAIL captured ✓ │ │ TDD-GREEN: PASS verified ✓ │ │ STANDARDS: [N]/[N] sections compliant ✓ │ │ │ │ Proceeding to Gate 1 (DevOps)... │ └─────────────────────────────────────────────────┘

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

See "State Persistence Rule" section.

1. Proceed to Step 2.3.1 (Delivery Verification Exit Check)

### Step 2.3.1: Delivery Verification Exit Check (MANDATORY before Gate 1)

After Gate 0 PASS, delivery verification runs AS EXIT CRITERIA (not as a separate gate). This check is performed inside `ring:dev-implementation` as its Step 7 (Delivery Verification Exit Check). The orchestrator DOES NOT dispatch a separate skill.

Verify that the dev-implementation handoff includes `delivery_verification` field:

required_handoff_fields: - implementation_summary - files_changed - tests_written - tdd_red_evidence - tdd_green_evidence - delivery_verification: result: "PASS|PARTIAL|FAIL" requirements_total: int requirements_delivered: int requirements_missing: int dead_code_items: int

IF delivery_verification.result == "PASS": → Update state.tasks[current].subtasks[current].gate_progress.implementation.delivery_verified = true → Proceed to Gate 1 (DevOps)

IF delivery_verification.result == "PARTIAL" or "FAIL": → Return control to dev-implementation with remediation instructions (max 2 retries) → After 2 retries → escalate to user

Anti-Rationalization:

| Rationalization | Why It's WRONG | Required Action |
| --- | --- | --- |
| "Gate 0.5 still exists, just renamed" | Gate 0.5 was DELETED as a separate dispatch. Checks now run inline in Gate 0. | **Read `delivery_verification` from Gate 0 handoff; do NOT dispatch a separate skill.** |
| "I'll just skip this check if Gate 0 passed" | Gate 0 passing without `delivery_verification` means Gate 0 is incomplete. | **Verify `delivery_verification` exists in handoff. If absent → Gate 0 failed.** |

No separate `state.gate_progress.delivery_verification` field — delivery verification is a sub-check of implementation, tracked inline.

### Anti-Rationalization: Gate 0 Skill Invocation

| Rationalization | Why It's WRONG | Required Action |
| --- | --- | --- |
| "I can run TDD-RED/GREEN directly from here" | Inline TDD = skipping the skill. Skill has iteration logic and validation. | **Invoke Skill("ring:dev-implementation")** |
| "I already know which agent to dispatch" | Agent selection is the SKILL's job, not the orchestrator's. | **Invoke Skill("ring:dev-implementation")** |
| "The TDD steps are documented here, I'll follow them" | These steps are REFERENCE, not EXECUTABLE. The skill is executable. | **Invoke Skill("ring:dev-implementation")** |
| "Skill adds overhead for simple tasks" | Overhead = compliance checks. Simple ≠ exempt. | **Invoke Skill("ring:dev-implementation")** |
| "I'll dispatch the agent and verify output myself" | Self-verification skips the skill's re-dispatch loop. | **Invoke Skill("ring:dev-implementation")** |
| "Agent already did TDD internally" | Internal ≠ verified by skill. Skill validates output structure. | **Invoke Skill("ring:dev-implementation")** |

---

## Step 3: Gate 1 - DevOps (Per Task — after all subtasks complete Gate 0 + Gate 3 + Gate 9)

⛔ **CADENCE:** This gate runs ONCE per task, NOT per subtask. Do NOT dispatch during the subtask loop. Input `implementation_files` is the UNION of all subtasks' changed files; `gate0_handoffs` is an ARRAY of per-subtask implementation handoffs.

**REQUIRED SUB-SKILLS:** Use ring:dev-devops, then ring:dev-docker-security (audit)

### ⛔ HARD GATE: Required Artifacts MUST Be Created

**Gate 1 is a BLOCKING gate.** DevOps agent MUST create all required artifacts. If any artifact is missing:

- You CANNOT proceed to Gate 2
- You MUST re-dispatch to ring:devops-engineer to create missing artifacts
- You MUST verify all artifacts exist before proceeding

### Required Artifacts

**See [shared-patterns/standards-coverage-table.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../skills/shared-patterns/standards-coverage-table.md) → "ring:devops-engineer → devops.md" for all required sections.**

**Key artifacts from devops.md:**

- Containers (Dockerfile + Docker Compose)
- Makefile Standards (all required commands)
- Infrastructure as Code (if applicable)
- Helm charts (if K8s deployment)

### Step 3.1: Prepare Input for ring:dev-devops Skill

⛔ **Input scope:** TASK-level. `implementation_files` is the UNION of `files_changed` across all subtasks of the current task; `gate0_handoffs` is an ARRAY (one per subtask).

Gather from completed subtask-level gates of the current task:

task = state.tasks[state.current_task_index]

devops_input = { // REQUIRED - TASK-level identifiers (NOT subtask) unit_id: task.id, // TASK id (e.g., "T-001"), not subtask id language: task.language, // "go" | "typescript" | "python" service_type: task.service_type, // "api" | "worker" | "batch" | "cli"

// REQUIRED - UNION of files changed across all subtasks of this task implementation_files: flatten(task.subtasks.map(st => st.gate_progress.implementation.files_changed || [] )),

// REQUIRED - ARRAY of per-subtask Gate 0 handoffs (one per subtask) gate0_handoffs: task.subtasks.map(st => st.gate_progress.implementation),

// OPTIONAL - additional context (union across subtasks where applicable) new_dependencies: union(task.subtasks.map(st => st.new_deps || [])), new_env_vars: union(task.subtasks.map(st => st.env_vars || [])), new_services: union(task.subtasks.map(st => st.services || [])), existing_dockerfile: [check if Dockerfile exists], existing_compose: [check if docker-compose.yml exists] }

### Step 3.2: Invoke ring:dev-devops Skill

1. Record gate start timestamp

1. Invoke ring:dev-devops skill with structured input:

Skill("ring:dev-devops") with input: unit_id: devops_input.unit_id # TASK id language: devops_input.language service_type: devops_input.service_type implementation_files: devops_input.implementation_files # UNION across subtasks gate0_handoffs: devops_input.gate0_handoffs # ARRAY of subtask handoffs new_dependencies: devops_input.new_dependencies new_env_vars: devops_input.new_env_vars new_services: devops_input.new_services existing_dockerfile: devops_input.existing_dockerfile existing_compose: devops_input.existing_compose

The skill handles: - Dispatching ring:devops-engineer agent - Dockerfile creation/update - docker-compose.yml configuration - .env.example documentation - Verification commands execution - Fix iteration loop (max 3 attempts)

1. Parse skill output for results:

Expected output sections: - "## DevOps Summary" → status, iterations - "## Files Changed" → Dockerfile, docker-compose, .env.example actions - "## Verification Results" → build, startup, health checks - "## Handoff to Next Gate" → ready_for_sre: YES/no

if skill output contains "Status: PASS" and "Ready for Gate 2: YES": → Gate 1 PASSED. Proceed to Step 3.3.

if skill output contains "Status: FAIL" or "Ready for Gate 2: no": → Gate 1 BLOCKED. → Skill already dispatched fixes to ring:devops-engineer → Skill already re-ran verification → If "ESCALATION" in output: STOP and report to user

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 3.2.1: Docker Security Audit

After ring:dev-devops PASSES, run Docker Hub Health Score compliance audit on the created/updated Dockerfile:

Skill("ring:dev-docker-security") with input: dockerfile_path: [extract from devops "## Files Changed" table, or default to "Dockerfile"] language: devops_input.language service_type: devops_input.service_type mode: "audit"

The skill validates: - Non-root USER directive - Minimal base image (distroless/alpine) - No AGPL v3 license risk - Supply chain attestations in pipeline - Audit checklist compliance

if skill output contains "Result: PASS": → Proceed to Step 3.3.

if skill output contains "Result: FAIL": → Re-dispatch ring:devops-engineer with the failing policies → Re-run ring:dev-docker-security audit → Max 3 total attempts (2 retries). If still FAIL: STOP and report to user

### Step 3.3: Gate 1 Complete

1. When ring:dev-devops skill returns PASS:

Parse from skill output: - status: extract from "## DevOps Summary" - dockerfile_action: extract from "## Files Changed" table - compose_action: extract from "## Files Changed" table - verification_passed: extract from "## Verification Results"

- agent_outputs.devops = { skill: "ring:dev-devops", output: "[full skill output]", artifacts_created: ["Dockerfile", "docker-compose.yml", ".env.example"], verification_passed: true, timestamp: "[ISO timestamp]", duration_ms: [execution time] }

1. Update state:

- gate_progress.devops.status = "completed" - gate_progress.devops.artifacts = [list from skill output]

1. Proceed to Gate 2

### Gate 1 Anti-Rationalization Table

| Rationalization | Why It's WRONG | Required Action |
| --- | --- | --- |
| "Dockerfile exists, skip other artifacts" | all artifacts required. 1/4 ≠ complete. | **Create all artifacts** |
| "docker-compose not needed locally" | docker-compose is MANDATORY for local dev. | **Create docker-compose.yml** |
| "Makefile is optional" | Makefile is MANDATORY for standardized commands. | **Create Makefile** |
| ".env.example can be added later" | .env.example documents required config NOW. | **Create.env.example** |
| "Small service doesn't need all this" | Size is irrelevant. Standards apply uniformly. | **Create all artifacts** |

## Step 4: Gate 2 - SRE (Per Task — after all subtasks complete Gate 0 + Gate 3 + Gate 9)

⛔ **CADENCE:** This gate runs ONCE per task, NOT per subtask. Input `implementation_files` is the UNION of all subtasks' changed files; `gate0_handoffs` is an ARRAY.

**REQUIRED SUB-SKILL:** Use `ring:dev-sre`

### Step 4.1: Prepare Input for ring:dev-sre Skill

⛔ **Input scope:** TASK-level. Aggregate from all subtasks of the current task.

Gather from completed subtask-level gates:

task = state.tasks[state.current_task_index]

sre_input = { // REQUIRED - TASK-level identifiers unit_id: task.id, // TASK id language: task.language, service_type: task.service_type,

// REQUIRED - UNION across subtasks implementation_files: flatten(task.subtasks.map(st => st.gate_progress.implementation.files_changed || [] )),

// REQUIRED - ARRAY of per-subtask Gate 0 handoffs gate0_handoffs: task.subtasks.map(st => st.gate_progress.implementation),

// REQUIRED - implementation_agent (consistent across subtasks of the same task) implementation_agent: task.subtasks[0].gate_progress.implementation.agent,

// OPTIONAL - additional context external_dependencies: task.external_deps || state.detected_dependencies || [], gate1_handoff: task.gate_progress.devops // task-level Gate 1 output (just completed) }

### Step 4.2: Invoke ring:dev-sre Skill

1. Record gate start timestamp

1. Invoke ring:dev-sre skill with structured input:

Skill("ring:dev-sre") with input: unit_id: sre_input.unit_id # TASK id language: sre_input.language service_type: sre_input.service_type implementation_agent: sre_input.implementation_agent implementation_files: sre_input.implementation_files # UNION across subtasks external_dependencies: sre_input.external_dependencies gate0_handoffs: sre_input.gate0_handoffs # ARRAY of subtask handoffs gate1_handoff: sre_input.gate1_handoff

The skill handles: - Dispatching SRE agent for validation - Structured logging validation - Distributed tracing validation - Code instrumentation coverage (90%+ required) - Context propagation validation (InjectHTTPContext/InjectGRPCContext) - Dispatching fixes to implementation agent if needed - Re-validation loop (max 3 iterations)

1. Parse skill output for validation results:

Expected output sections: - "## Validation Result" → status, iterations, coverage - "## Instrumentation Coverage" → table with per-layer coverage - "## Issues Found" → list or "None" - "## Handoff to Next Gate" → ready_for_testing: YES/no

if skill output contains "Status: PASS" and "Ready for Gate 3: YES": → Gate 2 PASSED. Proceed to Step 4.3.

if skill output contains "Status: FAIL" or "Ready for Gate 3: no": → Gate 2 BLOCKED. → Skill already dispatched fixes to implementation agent → Skill already re-ran validation → If "ESCALATION" in output: STOP and report to user

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 4.3: Gate 2 Complete

1. When ring:dev-sre skill returns PASS:

Parse from skill output: - status: extract from "## Validation Result" - instrumentation_coverage: extract percentage from coverage table - iterations: extract from "Iterations:" line

- agent_outputs.sre = { skill: "ring:dev-sre", output: "[full skill output]", validation_result: "PASS", instrumentation_coverage: "[X%]", iterations: [count], timestamp: "[ISO timestamp]", duration_ms: [execution time] }

1. Update state:

- gate_progress.sre.status = "completed" - gate_progress.sre.observability_validated = true - gate_progress.sre.instrumentation_coverage = "[X%]"

1. Proceed to Gate 3

### Gate 2 Anti-Rationalization Table

See [ring:dev-sre/SKILL.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../dev-sre/SKILL.md) for complete anti-rationalization tables covering:

- Observability deferral rationalizations
- Instrumentation coverage rationalizations
- Context propagation rationalizations

### Gate 2 Pressure Resistance

| User Says | Your Response |
| --- | --- |
| "Skip SRE validation, we'll add observability later" | "Observability is MANDATORY for Gate 2. Invoking ring:dev-sre skill now." |
| "SRE found issues but let's continue" | "Gate 2 is a HARD GATE. ring:dev-sre skill handles fix dispatch and re-validation." |
| "Instrumentation coverage is low but code works" | "90%+ instrumentation coverage is REQUIRED. ring:dev-sre skill will not pass until met." |

## Step 5: Gate 3 - Unit Testing (Per Execution Unit)

ℹ️ **CADENCE:** Subtask-level. Execution unit = a subtask (or the task itself when no subtasks). Writes to `state.tasks[i].subtasks[j].gate_progress.unit_testing`.

**REQUIRED SUB-SKILL:** Use `ring:dev-unit-testing`

### Step 5.1: Prepare Input for ring:dev-unit-testing Skill

Gather from previous gates:

testing_input = { // REQUIRED - from current execution unit unit_id: state.current_unit.id, acceptance_criteria: state.current_unit.acceptance_criteria, // list of ACs to test implementation_files: agent_outputs.implementation.files_changed, language: state.current_unit.language, // "go" | "typescript" | "python"

// OPTIONAL - additional context coverage_threshold: 85, // Ring minimum, PROJECT_RULES.md can raise gate0_handoff: agent_outputs.implementation, // full Gate 0 output existing_tests: [check for existing test files] }

### Step 5.2: Invoke ring:dev-unit-testing Skill

1. Record gate start timestamp

1. Invoke ring:dev-unit-testing skill with structured input:

Skill("ring:dev-unit-testing") with input: unit_id: testing_input.unit_id acceptance_criteria: testing_input.acceptance_criteria implementation_files: testing_input.implementation_files language: testing_input.language coverage_threshold: testing_input.coverage_threshold gate0_handoff: testing_input.gate0_handoff existing_tests: testing_input.existing_tests

The skill handles: - Dispatching ring:qa-analyst agent - Test creation following TDD methodology - Coverage measurement and validation (85%+ required) - Traceability matrix (AC → Test mapping) - Dispatching fixes to implementation agent if coverage < threshold - Re-validation loop (max 3 iterations)

1. Parse skill output for results:

Expected output sections: - "## Testing Summary" → status, iterations - "## Coverage Report" → threshold vs actual - "## Traceability Matrix" → AC-to-test mapping - "## Handoff to Next Gate" → ready_for_review: YES/no

if skill output contains "Status: PASS" and "Ready for Next Gate: YES": → Gate 3 PASSED. Proceed to Step 5.3.

if skill output contains "Status: FAIL" or "Ready for Next Gate: NO": → Gate 3 BLOCKED. → Skill already dispatched fixes to implementation agent → Skill already re-ran coverage check → If "ESCALATION" in output: STOP and report to user

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 5.3: Gate 3 Complete

1. When ring:dev-unit-testing skill returns PASS:

Parse from skill output: - coverage_actual: extract percentage from "## Coverage Report" - coverage_threshold: extract from "## Coverage Report" - criteria_covered: extract from "## Traceability Matrix" - iterations: extract from "Iterations:" line

- agent_outputs.testing = { skill: "ring:dev-unit-testing", output: "[full skill output]", verdict: "PASS", coverage_actual: [X%], coverage_threshold: [85%], criteria_covered: "[X/Y]", iterations: [count], timestamp: "[ISO timestamp]", duration_ms: [execution time], failures: [], // Empty when PASS; see schema below for FAIL uncovered_criteria: [] // Empty when all ACs covered }

If iterations > 1 (tests failed before passing), populate failures[]:

   failures: [
     {
       "test_name": "TestUserCreate_InvalidEmail",
       "test_file": "internal/handler/user_test.go",
       "error_type": "assertion|panic|timeout|compilation",
       "expected": "[expected value]",
       "actual": "[actual value]",
       "message": "[error message from test output]",
       "stack_trace": "[relevant stack trace]",
       "fixed_in_iteration": [iteration number when fixed]
     }
   ]

If coverage < 100% of acceptance criteria, populate uncovered_criteria[]:

uncovered_criteria: [
  {
    "criterion_id": "AC-001",
    "description": "User should receive email confirmation",
    "reason": "No test found for email sending functionality"
  }
]

1. Update state:

- gate_progress.testing.status = "completed" - gate_progress.testing.coverage = [coverage_actual]

1. Proceed to Gate 4 (Fuzz Testing)

### Gate 3 Thresholds

- **Minimum:** 85% (Ring standard - CANNOT be lowered)
- **Project-specific:** Can be higher if defined in `docs/PROJECT_RULES.md`
- **Validation:** Threshold < 85% → Use 85%

### Gate 3 Pressure Resistance

| User Says | Your Response |
|-----------|---------------|
| "84% is close enough" | "85% is Ring minimum. ring:dev-unit-testing skill enforces this." |
| "Skip testing, deadline" | "Testing is MANDATORY. ring:dev-unit-testing skill handles iterations." |
| "Manual testing covers it" | "Gate 3 requires executable unit tests. Invoking ring:dev-unit-testing now." |

## Step 6: Gate 4 - Fuzz Testing (Per Task — after all subtasks complete Gate 0 + Gate 3 + Gate 9)

⛔ **CADENCE:** This gate runs ONCE per task, NOT per subtask. Input `implementation_files` is the UNION of all subtasks' changed files.

**REQUIRED SUB-SKILL:** Use `ring:dev-fuzz-testing`

**MANDATORY GATE:** All code paths MUST have fuzz tests to discover edge cases and crashes.

### Step 6.1: Prepare Input for ring:dev-fuzz-testing Skill

⛔ **Input scope:** TASK-level. Aggregate from all subtasks of the current task.

task = state.tasks[state.current_task_index]

fuzz_testing_input = { // REQUIRED - TASK-level unit_id: task.id, // TASK id language: task.language, // "go" | "typescript"

// REQUIRED - UNION across subtasks implementation_files: flatten(task.subtasks.map(st => st.gate_progress.implementation.files_changed || [] )),

// REQUIRED - ARRAY of per-subtask unit-testing handoffs (Gate 3 is per subtask) gate3_handoffs: task.subtasks.map(st => st.gate_progress.unit_testing) }

### Step 6.2: Invoke ring:dev-fuzz-testing Skill

1. Record gate start timestamp

1. Invoke ring:dev-fuzz-testing skill with structured input:

Skill("ring:dev-fuzz-testing") with input: unit_id: fuzz_testing_input.unit_id # TASK id implementation_files: fuzz_testing_input.implementation_files # UNION across subtasks language: fuzz_testing_input.language gate3_handoffs: fuzz_testing_input.gate3_handoffs # ARRAY of per-subtask handoffs

The skill handles: - Dispatching ring:qa-analyst agent (test_mode: fuzz) - Fuzz function creation (FuzzXxx naming) - Seed corpus generation (minimum 5 entries) - f.Add() pattern validation - Dispatching fixes if crashes found - Re-validation loop (max 3 iterations)

1. Parse skill output for results:

if skill output contains "Status: PASS": → Gate 4 PASSED. Proceed to Gate 5.

if skill output contains "Status: FAIL": → Gate 4 BLOCKED.

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 6.3: Gate 4 Complete

1. Update state:

- gate_progress.fuzz_testing.status = "completed" - gate_progress.fuzz_testing.corpus_entries = [count]

1. Proceed to Gate 5 (Property Testing)

---

## Step 7: Gate 5 - Property-Based Testing (Per Task — after all subtasks complete Gate 0 + Gate 3 + Gate 9)

⛔ **CADENCE:** This gate runs ONCE per task, NOT per subtask. Input `implementation_files` is the UNION of all subtasks' changed files; `domain_invariants` is the UNION across subtasks.

**REQUIRED SUB-SKILL:** Use `ring:dev-property-testing`

**MANDATORY GATE:** Domain invariants MUST be verified with property-based tests.

### Step 7.1: Prepare Input for ring:dev-property-testing Skill

⛔ **Input scope:** TASK-level.

task = state.tasks[state.current_task_index]

property_testing_input = { // REQUIRED - TASK-level unit_id: task.id, // TASK id language: task.language,

// REQUIRED - UNION across subtasks implementation_files: flatten(task.subtasks.map(st => st.gate_progress.implementation.files_changed || [] )),

// Domain invariants — UNION across subtasks of the task domain_invariants: union(task.subtasks.map(st => st.domain_invariants || [])) }

### Step 7.2: Invoke ring:dev-property-testing Skill

1. Record gate start timestamp

1. Invoke ring:dev-property-testing skill with structured input:

Skill("ring:dev-property-testing") with input: unit_id: property_testing_input.unit_id implementation_files: property_testing_input.implementation_files language: property_testing_input.language domain_invariants: property_testing_input.domain_invariants

The skill handles: - Dispatching ring:qa-analyst agent (test_mode: property) - Property function creation (TestProperty_* naming) - quick.Check pattern validation - Invariant verification - Dispatching fixes if properties fail - Re-validation loop (max 3 iterations)

1. Parse skill output for results:

if skill output contains "Status: PASS": → Gate 5 PASSED. Proceed to Gate 6.

if skill output contains "Status: FAIL": → Gate 5 BLOCKED.

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 7.3: Gate 5 Complete

1. Update state:

- gate_progress.property_testing.status = "completed" - gate_progress.property_testing.properties_tested = [count]

1. Proceed to Gate 6 (Integration Testing)

---

## Step 8: Gate 6 - Integration Testing (Per Task — WRITE ONLY)

⛔ **CADENCE:** Write mode runs ONCE per task, NOT per subtask. Execute mode runs ONCE at cycle end (Step 12.1). Input `implementation_files` is the UNION of all subtasks' changed files.

**REQUIRED SUB-SKILL:** Use `ring:dev-integration-testing`

**MANDATORY GATE:** All code MUST have integration tests using testcontainers.

**⛔ DEFERRED EXECUTION:** Per task, this gate writes/updates integration test code and verifies compilation. Tests are NOT executed here (no containers). Actual execution happens at end of cycle (Step 12.1).

### Step 8.1: Prepare Input for ring:dev-integration-testing Skill

⛔ **Input scope:** TASK-level.

task = state.tasks[state.current_task_index]

integration_testing_input = { // REQUIRED - TASK-level unit_id: task.id, // TASK id language: task.language, mode: "write_only", // CRITICAL: write tests, verify compilation, do NOT execute

// REQUIRED - UNION across subtasks of the task integration_scenarios: union(task.subtasks.map(st => st.integration_scenarios || [])), external_dependencies: union(task.subtasks.map(st => st.external_dependencies || [])) || state.detected_dependencies || [], implementation_files: flatten(task.subtasks.map(st => st.gate_progress.implementation.files_changed || [] )),

// OPTIONAL - additional context gate5_handoff: task.gate_progress.property_testing // task-level Gate 5 output }

// NOTE: external_dependencies falls back to state.detected_dependencies // from Step 1.6 (cycle-level auto-detection) when no subtask defines them.

### Step 8.2: Invoke ring:dev-integration-testing Skill (Write Mode)

1. Record gate start timestamp

1. REQUIRED: Invoke ring:dev-integration-testing skill with structured input:

Skill("ring:dev-integration-testing") with input: unit_id: integration_testing_input.unit_id integration_scenarios: integration_testing_input.integration_scenarios external_dependencies: integration_testing_input.external_dependencies language: integration_testing_input.language mode: "write_only" gate5_handoff: integration_testing_input.gate5_handoff implementation_files: integration_testing_input.implementation_files

In write_only mode, the skill handles: - Dispatching ring:qa-analyst agent (test_mode: integration) - Writing/updating integration test code for current unit's changes - Verifying test compilation (go build ./... or tsc --noEmit) - Verifying build tags (//go:build integration) present - Verifying testcontainers imports present - NOT spinning up containers or executing tests

1. REQUIRED: Parse skill output for results:

Expected output: - "## Integration Test Code" → files written/updated - "## Compilation Check" → PASS/FAIL - "## Standards Compliance" → build tags, naming, testcontainers

if compilation PASS and standards met: → Gate 6 (write) PASSED. Proceed to Step 8.3.

if compilation FAIL: → Gate 6 BLOCKED. Fix compilation errors before proceeding.

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 8.3: Gate 6 (Write) Complete

1. Update state:

- gate_progress.integration_testing.write_status = "completed" - gate_progress.integration_testing.execution_status = "deferred" // Executed at end of cycle - gate_progress.integration_testing.test_files = [list of test files written/updated] - gate_progress.integration_testing.compilation_passed = true

1. Proceed to Gate 7 (Chaos Testing — Write Only)

### Gate 6 Pressure Resistance

| User Says | Your Response |
| --- | --- |
| "Unit tests cover integration" | "Unit tests mock dependencies. Integration tests verify real behavior. Write the tests now, execute at end of cycle." |
| "Skip writing, we'll add tests later" | "Test code MUST be written per unit to stay current. Only execution is deferred." |
| "No external dependencies to test" | "Verify internal integration too. Write the tests, they'll execute at end of cycle." |
| "Just run the tests now" | "Deferred execution avoids redundant container spin-ups. Tests execute once at end of cycle." |

---

## Step 9: Gate 7 - Chaos Testing (Per Task — WRITE ONLY)

⛔ **CADENCE:** Write mode runs ONCE per task, NOT per subtask. Execute mode runs ONCE at cycle end (Step 12.1). `external_dependencies` is the UNION across all subtasks of the task.

**REQUIRED SUB-SKILL:** Use `ring:dev-chaos-testing`

**MANDATORY GATE:** All external dependencies MUST have chaos tests for failure scenarios.

**⛔ DEFERRED EXECUTION:** Per task, this gate writes/updates chaos test code and verifies compilation. Tests are NOT executed here (no Toxiproxy). Actual execution happens at end of cycle (Step 12.1).

### Step 9.1: Prepare Input for ring:dev-chaos-testing Skill

⛔ **Input scope:** TASK-level.

task = state.tasks[state.current_task_index]

chaos_testing_input = { // REQUIRED - TASK-level unit_id: task.id, // TASK id language: task.language, mode: "write_only", // CRITICAL: write tests, verify compilation, do NOT execute

// REQUIRED - UNION across subtasks of the task external_dependencies: union(task.subtasks.map(st => st.external_dependencies || [])) || state.detected_dependencies || [], implementation_files: flatten(task.subtasks.map(st => st.gate_progress.implementation.files_changed || [] )),

// OPTIONAL - additional context gate6_handoff: task.gate_progress.integration_testing // task-level Gate 6 (write) output }

// NOTE: external_dependencies falls back to state.detected_dependencies // from Step 1.6 (cycle-level auto-detection) when no subtask defines them.

### Step 9.2: Invoke ring:dev-chaos-testing Skill (Write Mode)

1. Record gate start timestamp

1. REQUIRED: Invoke ring:dev-chaos-testing skill with structured input:

Skill("ring:dev-chaos-testing") with input: unit_id: chaos_testing_input.unit_id external_dependencies: chaos_testing_input.external_dependencies language: chaos_testing_input.language mode: "write_only" gate6_handoff: chaos_testing_input.gate6_handoff

In write_only mode, the skill handles: - Dispatching ring:qa-analyst agent (test_mode: chaos) - Writing/updating chaos test code for current unit's dependencies - Verifying test compilation - Verifying dual-gate pattern (CHAOS=1 + testing.Short()) - Verifying Toxiproxy imports present - NOT starting Toxiproxy or executing failure scenarios

1. Parse skill output for results:

if compilation PASS and standards met: → Gate 7 (write) PASSED. Proceed to Gate 8.

if compilation FAIL: → Gate 7 BLOCKED. Fix compilation errors before proceeding.

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 9.3: Gate 7 (Write) Complete

1. Update state:

- gate_progress.chaos_testing.write_status = "completed" - gate_progress.chaos_testing.execution_status = "deferred" // Executed at end of cycle - gate_progress.chaos_testing.test_files = [list of test files written/updated] - gate_progress.chaos_testing.compilation_passed = true

1. Proceed to Gate 8 (Review)

### Gate 7 Pressure Resistance

| User Says | Your Response |
| --- | --- |
| "Chaos testing is overkill" | "Chaos tests verify graceful degradation. Write them now, execute at end of cycle." |
| "Skip writing, add later" | "Test code MUST be written per unit. Only execution is deferred to end of cycle." |
| "Just run the chaos tests now" | "Deferred execution avoids redundant Toxiproxy spin-ups. Tests execute once at end of cycle." |
| "No time for chaos testing" | "Writing chaos tests per unit takes minutes. Execution cost is paid once at end." |

---

## Step 10: Gate 8 - Review (Per Task — after all subtasks complete Gate 0 + Gate 3 + Gate 9)

⛔ **CADENCE:** This gate runs ONCE per task, NOT per subtask. Reviewers see the CUMULATIVE diff of all subtasks in the task — cross-subtask interaction bugs (contract drift, hidden coupling, duplicated logic) are MORE visible at this cadence, not less.

**REQUIRED SUB-SKILL:** Use `ring:codereview`

### Step 10.1: Prepare Input for ring:codereview Skill

⛔ **Input scope:** TASK-level. `base_sha` is the SHA before the FIRST subtask's Gate 0 (i.e., the task's starting commit); `head_sha` is the current HEAD after all subtasks and task-level gates up to this point. The resulting diff covers ALL subtasks of the task.

task = state.tasks[state.current_task_index]

review_input = { // REQUIRED - TASK-level unit_id: task.id, // TASK id base_sha: task.base_sha, // SHA before the FIRST subtask started head_sha: [current HEAD], // SHA after all subtasks + task-level gates so far

// REQUIRED - summary and requirements aggregated from task + subtasks implementation_summary: task.title + "\n" + task.subtasks.map(st => "- " + st.title + ": " + (st.summary || "")).join("\n"), requirements: task.acceptance_criteria || flatten(task.subtasks.map(st => st.acceptance_criteria || [])),

// OPTIONAL - additional context implementation_files: flatten(task.subtasks.map(st => st.gate_progress.implementation.files_changed || [] )), // UNION across subtasks gate0_handoffs: task.subtasks.map(st => st.gate_progress.implementation) // ARRAY }

### Step 10.2: Invoke ring:codereview Skill

1. Record gate start timestamp

1. Invoke ring:codereview skill with structured input:

Skill("ring:codereview") with input: unit_id: review_input.unit_id # TASK id base_sha: review_input.base_sha # SHA before first subtask head_sha: review_input.head_sha # Current HEAD (cumulative diff) implementation_summary: review_input.implementation_summary requirements: review_input.requirements implementation_files: review_input.implementation_files # UNION across subtasks gate0_handoffs: review_input.gate0_handoffs # ARRAY of subtask handoffs

The skill handles: - Dispatching all 10 reviewers in PARALLEL (single message with 10 Task calls) - ring:code-reviewer, ring:business-logic-reviewer, ring:security-reviewer, ring:nil-safety-reviewer, ring:test-reviewer, ring:consequences-reviewer, ring:dead-code-reviewer, ring:performance-reviewer, ring:multi-tenant-reviewer, ring:lib-commons-reviewer - Aggregating issues by severity (CRITICAL/HIGH/MEDIUM/LOW/COSMETIC) - Dispatching fixes to implementation agent for blocking issues - Re-running all 10 reviewers after fixes - Iteration tracking (max 3 attempts) - Adding TODO/FIXME comments for non-blocking issues

1. Parse skill output for results:

Expected output sections: - "## Review Summary" → status, iterations - "## Issues by Severity" → counts per severity level - "## Reviewer Verdicts" → all 10 reviewers - "## Handoff to Next Gate" → ready_for_validation: YES/NO

if skill output contains "Status: PASS" and "Ready for Gate 9: YES": → Gate 8 PASSED. Proceed to Step 10.3.

if skill output contains "Status: FAIL" or "Ready for Gate 9: NO": → Gate 8 BLOCKED. → Skill already dispatched fixes to implementation agent → Skill already re-ran all 10 reviewers → If "ESCALATION" in output: STOP and report to user

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 10.3: Gate 8 Complete

1. When ring:codereview skill returns PASS:

Parse from skill output: - reviewers_passed: extract from "## Reviewer Verdicts" (should be "5/5") - issues_critical: extract count from "## Issues by Severity" - issues_high: extract count from "## Issues by Severity" - issues_medium: extract count from "## Issues by Severity" - iterations: extract from "Iterations:" line

- agent_outputs.review = { skill: "ring:codereview", output: "[full skill output]", iterations: [count], timestamp: "[ISO timestamp]", duration_ms: [execution time], reviewers_passed: "5/5", code_reviewer: { verdict: "PASS", issues_count: N, issues: [] // Structured issues - see schema below }, business_logic_reviewer: { verdict: "PASS", issues_count: N, issues: [] }, security_reviewer: { verdict: "PASS", issues_count: N, issues: [] }, nil_safety_reviewer: { verdict: "PASS", issues_count: N, issues: [] }, test_reviewer: { verdict: "PASS", issues_count: N, issues: [] } }

Populate issues[] for each reviewer with all issues found (even if fixed):

   issues: [
     {
       "severity": "CRITICAL|HIGH|MEDIUM|LOW|COSMETIC",
       "category": "error-handling|security|performance|maintainability|business-logic|...",
       "description": "[detailed description of the issue]",
       "file": "internal/handler/user.go",
       "line": 45,
       "code_snippet": "return err",
       "suggestion": "Use fmt.Errorf(\"failed to create user: %w\", err)",
       "fixed": true|false,
       "fixed_in_iteration": [iteration number when fixed, null if not fixed]
     }
   ]

Issue tracking rules:

• all issues found across all iterations MUST be recorded
• fixed: true + fixed_in_iteration: N for issues resolved during review
• fixed: false + fixed_in_iteration: null for LOW/COSMETIC (TODO/FIXME added)
• This enables feedback-loop to analyze recurring issue patterns

1. Update state:

- gate_progress.review.status = "completed" - gate_progress.review.reviewers_passed = "5/5"

1. Proceed to Gate 9

### Gate 8 Anti-Rationalization Table

| Rationalization | Why It's WRONG | Required Action |
|-----------------|----------------|-----------------|
| "Only 1 MEDIUM issue, can proceed" | MEDIUM = MUST FIX. Quantity is irrelevant. | **Fix the issue, re-run all 10 reviewers** |
| "Issue is cosmetic, not really MEDIUM" | Reviewer decided severity. Accept their judgment. | **Fix the issue, re-run all 10 reviewers** |
| "Will fix in next sprint" | Deferred fixes = technical debt = production bugs. | **Fix NOW before Gate 9** |
| "User approved, can skip fix" | User approval ≠ reviewer override. Fixes are mandatory. | **Fix the issue, re-run all 10 reviewers** |
| "Same issue keeps appearing, skip it" | Recurring issue = fix is wrong. Debug properly. | **Root cause analysis, then fix** |
| "Only one reviewer found it" | One reviewer = valid finding. All findings matter. | **Fix the issue, re-run all 10 reviewers** |
| "Iteration limit reached, just proceed" | Limit = escalate, not bypass. Quality is non-negotiable. | **Escalate to user, DO NOT proceed** |
| "Tests pass, review issues don't matter" | Tests ≠ review. Different quality dimensions. | **Fix the issue, re-run all 10 reviewers** |

### Gate 8 Pressure Resistance

| User Says | Your Response |
|-----------|---------------|
| "Just skip this MEDIUM issue" | "MEDIUM severity issues are blocking by definition. I MUST dispatch a fix to the appropriate agent before proceeding. This protects code quality." |
| "I'll fix it later, let's continue" | "Gate 8 is a HARD GATE. All CRITICAL/HIGH/MEDIUM issues must be resolved NOW. I'm dispatching the fix to [agent] and will re-run all 10 reviewers after." |
| "We're running out of time" | "Proceeding with known issues creates larger problems later. The fix dispatch is automated and typically takes 2-5 minutes. Quality gates exist to save time overall." |
| "Override the gate, I approve" | "User approval cannot override reviewer findings. The gate ensures code quality. I'll dispatch the fix now." |
| "It's just a style issue" | "If it's truly cosmetic, reviewers would mark it COSMETIC (non-blocking). MEDIUM means it affects maintainability or correctness. Fixing now." |

---

## Step 11: Gate 9 - Validation (Per Execution Unit)

ℹ️ **CADENCE:** Subtask-level. Runs after Gate 3 for the current subtask (or task-itself when no subtasks). Writes to `state.tasks[i].subtasks[j].gate_progress.validation`. Task-level gates (1, 2, 4, 5, 6w, 7w, 8) only run AFTER every subtask of the task has passed Gates 0, 3, and 9.

For current execution unit:

1. Record gate start timestamp
2. Verify acceptance criteria:

For each criterion in acceptance_criteria: - Check if implemented - Check if tested - Mark as PASS/FAIL

1. Run final verification:

- All tests pass? - No Critical/High/Medium review issues? - All acceptance criteria met?

1. If validation fails:

- Log failure reasons - Determine which gate to revisit - Loop back to appropriate gate

1. If validation passes:

- Set unit status = "completed" - Record gate end timestamp - agent_outputs.validation = { result: "approved", timestamp: "[ISO timestamp]", criteria_results: [{criterion, status}] } - Proceed to Step 11.1 (Execution Unit Approval)

## Step 11.1: Execution Unit Approval (Conditional)

**Checkpoint depends on `execution_mode`:** `manual_per_subtask` → Execute | `manual_per_task` / `automatic` → Skip

1. **COMMIT CHECK (before checkpoint):**
  - if `commit_timing == "per_subtask"`:
    - Execute `/ring:commit` command with message: `feat({unit_id}): {unit_title}`
    - Include all changed files from this subtask
  - else: Skip commit (will happen at task or cycle end)

0b. **VISUAL CHANGE REPORT (subtask-level — OPT-IN ONLY):**

- Default: SKIP per-subtask visual report. Task-level aggregate report is generated in Step 11.2.
- Opt-in: If `state.visual_report_granularity == "subtask"`, generate per-subtask report. Default value is "task".
- Rationale: Task-level aggregate covers all subtasks' diffs; per-subtask reports are rarely consumed and cost one visualize dispatch each.

1. Set `status = "paused_for_approval"`, save state
2. Present summary: Unit ID, Parent Task, Gates 0-9 status, Criteria X/X, Duration, Files Changed, Commit Status
3. **AskUserQuestion:** "Ready to proceed?" Options: (a) Continue (b) Test First (c) Stop Here
4. **Handle response:**

| Response | Action |
| --- | --- |
| Continue | Set in_progress, move to next unit (or Step 11.2 if last) |
| Test First | Set `paused_for_testing`, STOP, output resume command |
| Stop Here | Set `paused`, STOP, output resume command |

## Step 11.2: Task Approval Checkpoint (Conditional)

**Checkpoint depends on `execution_mode`:** `manual_per_subtask` / `manual_per_task` → Execute | `automatic` → Skip

1. **COMMIT CHECK (before task checkpoint):**
  - if `commit_timing == "per_task"`:
    - Execute `/ring:commit` command with message: `feat({task_id}): {task_title}`
    - Include all changed files from this task (all subtasks combined)
  - else if `commit_timing == "per_subtask"`: Already committed per subtask
  - else: Skip commit (will happen at cycle end)

0b. **VISUAL CHANGE REPORT (MANDATORY - before task checkpoint):**

- MANDATORY: Invoke `Skill("ring:visualize")` to generate an aggregate code-diff HTML report for all subtasks in this task
- Read `default/skills/visualize/templates/code-diff.html` to absorb the patterns before generating
- Content aggregated from all subtask executions:
  - **Task Overview:** Task ID, title, all subtask IDs and their gate statuses
  - **Combined File Changes:** All files modified across all subtasks with before/after diff panels
  - **Aggregate Metrics:** Total tests added, total review iterations, total lines changed
- Save to: `docs/ring:dev-cycle/reports/task-{task_id}-report.html`
- Open in browser: `macOS: open docs/ring:dev-cycle/reports/task-{task_id}-report.html Linux: xdg-open docs/ring:dev-cycle/reports/task-{task_id}-report.html`
- Tell the user the file path
- See [shared-patterns/anti-rationalization-visual-report.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../shared-patterns/anti-rationalization-visual-report.md) for anti-rationalization table

1. Set task `status = "completed"`, cycle `status = "paused_for_task_approval"`, save state, and update tasks.md Status → `✅ Done` (per Step 11.2 row in State Persistence Checkpoints table)
2. Present summary: Task ID, Subtasks X/X, Total Duration, Review Iterations, Files Changed, Commit Status
3. **AskUserQuestion:** "Task complete. Ready for next?" Options: (a) Continue (b) Integration Test (c) Stop Here
4. **Handle response:**

After completing all subtasks of a task:

1. Check execution_mode from state:

- If "automatic": Still run feedback, then skip to next task - If "manual_per_subtask" or "manual_per_task": Continue with checkpoint below

1. Set task status = "completed"

1. Accumulate task metrics into state (NO dev-report dispatch here):

Write into state.tasks[current_task_index].accumulated_metrics: - gate_durations_ms: {gate_name: duration_ms for each completed gate} - review_iterations: state.tasks[current].gate_progress.review.iterations - testing_iterations: sum across all testing gates (unit, fuzz, property, integration, chaos) - issues_by_severity: {CRITICAL, HIGH, MEDIUM, LOW counts from Gate 8 output}

Set state.tasks[current].feedback_loop_completed = true (Actual dev-report dispatch happens ONCE at cycle end in Step 12.1.)

MANDATORY: Save state to file.

Rationale: Feedback analysis is stronger on aggregate data. A single cycle-end dev-report run produces the same or better insights than N per-task runs.

1. Set cycle status = "paused_for_task_approval"
2. Save state

1. Present task completion summary (with feedback metrics):

┌─────────────────────────────────────────────────┐ │ ✓ TASK COMPLETED │ ├─────────────────────────────────────────────────┤ │ Task: [task_id] - [task_title] │ │ │ │ Subtasks Completed: X/X │ │ ✓ ST-001-01: [title] │ │ ✓ ST-001-02: [title] │ │ ✓ ST-001-03: [title] │ │ │ │ Total Duration: Xh Xm │ │ Total Review Iterations: N │ │ │ │ ═══════════════════════════════════════════════ │ │ FEEDBACK METRICS │ │ ═══════════════════════════════════════════════ │ │ │ │ Assertiveness Score: XX% (Rating) │ │ │ │ Prompt Quality by Agent: │ │ ring:backend-engineer-golang: 90% (Excellent) │ │ ring:qa-analyst: 75% (Acceptable) │ │ ring:code-reviewer: 88% (Good) │ │ │ │ Improvements Suggested: N │ │ Feedback Location: │ │ docs/feedbacks/cycle-YYYY-MM-DD/ │ │ │ │ ═══════════════════════════════════════════════ │ │ │ │ All Files Changed This Task: │ │ - file1.go │ │ - file2.go │ │ - ... │ │ │ │ Next Task: [next_task_id] - [next_task_title] │ │ Subtasks: N (or "TDD autonomous") │ │ or "No more tasks - cycle complete" │ └─────────────────────────────────────────────────┘

1. ASK FOR EXPLICIT APPROVAL using AskUserQuestion tool:

Question: "Task [task_id] complete. Ready to start the next task?" Options: a) "Continue" - Proceed to next task b) "Integration Test" - User wants to test the full task integration c) "Stop Here" - Pause cycle

1. Handle user response:

If "Continue": - Set status = "in_progress" - Move to next task - Set current_task_index += 1 - Set current_subtask_index = 0 - Reset to Gate 0 - Continue execution

If "Integration Test": - Set status = "paused_for_integration_testing" - Save state - Output: "Cycle paused for integration testing. Test task [task_id] integration and run: /ring:dev-cycle --resume when ready to continue." - STOP execution

If "Stop Here": - Set status = "paused" - Save state - Output: "Cycle paused after task [task_id]. Resume with: /ring:dev-cycle --resume" - STOP execution

**Note:** Tasks without subtasks execute both 7.1 and 7.2 in sequence.

## Step 12: Cycle Completion

### Step 12.0: Deferred Test Execution (Gates 6-7)

**⛔ MANDATORY: Execute integration and chaos tests before final commit.**

All units have written/updated test code during their Gate 6-7 passes. Now execute all tests once.

1. Record deferred execution start timestamp

1. REQUIRED: Invoke ring:dev-integration-testing skill in EXECUTE mode:

Skill("ring:dev-integration-testing") with input: mode: "execute" all_test_files: [aggregate gate_progress.integration_testing.test_files from all units] language: state.language

The skill handles: - Spinning up testcontainers for all external dependencies - Running ALL integration tests across all units - Reporting pass/fail per test file - If failures: dispatching fixes and re-running (max 3 iterations)

1. REQUIRED: Invoke ring:dev-chaos-testing skill in EXECUTE mode:

Skill("ring:dev-chaos-testing") with input: mode: "execute" all_test_files: [aggregate gate_progress.chaos_testing.test_files from all units] language: state.language

The skill handles: - Starting Toxiproxy - Running ALL chaos tests across all units - Verifying recovery for all failure scenarios - If failures: dispatching fixes and re-running (max 3 iterations)

1. Update state:

- gate_progress.integration_testing.execution_status = "completed" (or "failed") - gate_progress.chaos_testing.execution_status = "completed" (or "failed")

1. if any test FAILS after 3 iterations:

→ HARD BLOCK. Cannot complete cycle. → Report failures to user.

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

### Step 12.0 Anti-Rationalization

| Rationalization | Why It's WRONG | Required Action |
| --- | --- | --- |
| "All unit/fuzz/property tests passed, skip integration" | Different test types catch different bugs. All are MANDATORY. | **Execute deferred tests** |
| "Tests were written, that's enough" | Written ≠ passing. Execution verifies real behavior. | **Execute deferred tests** |
| "Containers are slow, let CI handle it" | CI is backup, not replacement. Verify locally first. | **Execute deferred tests** |
| "One test failed but it's flaky" | Flaky = unreliable = fix it. No exceptions. | **Fix and re-run** |

### Step 12.0.5: Multi-Tenant Verification (Post-Cycle — Verification Only)

**Multi-tenant dual-mode is now implemented during Gate 0 and verified at Gate 0.5G.** This post-cycle step is a final sanity check only — it does NOT implement or adapt any code.

1. Verify Gate 0.5G passed for ALL units:

for each task in state.tasks: for each unit in task.units: if unit.gate_progress.delivery_verification.mt_dualmode != "PASS": → HARD BLOCK: "Unit [unit_id] failed MT dual-mode verification at Gate 0.5G" → This should never happen (Gate 0.5G blocks progression)

1. Display to user:

┌─────────────────────────────────────────────────┐ │ ✓ MULTI-TENANT DUAL-MODE VERIFIED │ ├─────────────────────────────────────────────────┤ │ Mode: Dual-mode (implemented at Gate 0) │ │ Verification: Gate 0.5G PASS for all units │ │ Resources Covered: [PG/Mongo/Redis/RMQ/S3] │ │ Backward Compat: Resolvers handle single-tenant │ └─────────────────────────────────────────────────┘

1. MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]

**Note:** The full ring:dev-multi-tenant skill (12 gates) targets legacy single-tenant codebases being migrated to dual-mode. For new development via dev-cycle, multi-tenant compliance is handled inline by Gate 0 (implementation) + Gate 0.5G (verification).

---

### Step 12.0.5b: Gate 0.5D — Migration Safety Verification (Conditional, Post-Cycle)

**CADENCE:** Post-cycle, conditional. Runs ONCE per cycle if SQL migration files are detected in the cycle diff. Parallel to Gate 0.5G.

**Purpose:** Static analysis on SQL migration files introduced by the cycle, per [migration-safety.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../../docs/standards/golang/migration-safety.md) and [shared-patterns/migration-safety-checks.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../shared-patterns/migration-safety-checks.md). Gate 0.5D is orthogonal to Gate 0.5G — 0.5G checks multi-tenant Go code safety; 0.5D checks SQL schema evolution safety.

**Trigger detection:**

MIGRATION_FILES=$(git diff --name-only origin/main...HEAD -- '**/migrations/*.sql' '**/*.sql' 2>/dev/null | grep -v "_test") if [ -z "$MIGRATION_FILES" ]: → Log: "No SQL migration files detected in cycle diff — Gate 0.5D skipped" → Write state.gate_progress.migration_safety_verification = {status: "skipped", reason: "no_migration_files"} → Proceed to Step 12.1 Final Commit else: → Proceed to Gate 0.5D checks below

**Check categories (from [migration-safety.md § Dangerous Operations](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../../docs/standards/golang/migration-safety.md#dangerous-operations-detection) + [shared-patterns/migration-safety-checks.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../shared-patterns/migration-safety-checks.md)):**

1. **BLOCKING** — `ADD COLUMN... NOT NULL` without `DEFAULT` (ACCESS EXCLUSIVE lock, table rewrite)
2. **BLOCKING** — `DROP COLUMN` (breaks services still reading; requires expand-contract)
3. **BLOCKING** — `DROP TABLE` / `TRUNCATE TABLE` (data loss)
4. **BLOCKING** — `CREATE INDEX` without `CONCURRENTLY` (SHARE lock blocks writes)
5. **BLOCKING** — `ALTER COLUMN TYPE` (table rewrite)
6. **BLOCKING** — Missing or empty `.down.sql` rollback migration
7. **WARN** — DDL without `IF NOT EXISTS` / `IF EXISTS` (not idempotent for multi-tenant re-runs)
8. **WARN** — Large `UPDATE` without batching (extended row locks)
9. **ACKNOWLEDGE** — Intentional `DROP COLUMN` that is the contract phase of a prior expand-contract sequence (author must confirm expand phase was already deployed)
10. **ACKNOWLEDGE** — `ALTER TYPE` on tables documented as > 100k rows (author must confirm maintenance plan)

**Execution (inline, mirrors verification commands in [migration-safety.md § Verification Commands](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../../docs/standards/golang/migration-safety.md#verification-commands)):**

1. Record gate start timestamp.

1. For each file in MIGRATION_FILES:

a. Run BLOCKING checks (steps 1–6 above). Collect findings with {file, line, pattern, severity: "BLOCKING"}. b. Run WARN checks (steps 7–8 above). Collect findings with severity: "WARN". c. Scan file for magic markers ("-- EXPAND-CONTRACT: contract phase" or "-- ACKNOWLEDGE: <rationale>") indicating an intentional breaking change. Reclassify matching BLOCKING findings → "ACKNOWLEDGE".

1. Verify paired DOWN migration:

For each *.up.sql in MIGRATION_FILES: → Expect *.down.sql in same directory, non-empty. → Missing/empty → BLOCKING finding.

1. Aggregate counts: {BLOCKING: N, WARN: N, ACKNOWLEDGE: N}.

**Decision logic:**

- **ANY BLOCKING finding** → HARD BLOCK: "Gate 0.5D failed: BLOCKING migration safety violation(s) in [files]. Cycle CANNOT proceed to Final Commit. Fix violation and re-run dev-cycle from the affected task, or mark as intentional via '-- ACKNOWLEDGE: ' inline comment if the operation is truly required (e.g., contract phase of a deployed expand-contract)."
- **ANY ACKNOWLEDGE finding** → Pause cycle at checkpoint. Display each finding with its `-- ACKNOWLEDGE:` rationale. Require user to respond with the exact phrase: "I acknowledge this breaking change and have verified the expand phase deployment." Any other response → HARD BLOCK.
- **Only WARN findings** → Log warnings in cycle summary, proceed to Final Commit.
- **Zero findings** → Log "Gate 0.5D PASSED — all migration files safe" and proceed.

**Report to user:**

┌─────────────────────────────────────────────────┐ │ ✓ MIGRATION SAFETY VERIFIED (Gate 0.5D) │ ├─────────────────────────────────────────────────┤ │ Files Checked: [count] │ │ BLOCKING: 0 WARN: N ACKNOWLEDGE: N │ │ Standard: docs/standards/golang/migration-safety│ └─────────────────────────────────────────────────┘

**State persistence:**

state.gate_progress.migration_safety_verification = { "status": "completed" | "skipped" | "blocked" | "acknowledged", "files_checked": ["path/to/migration.up.sql", ...], "findings": { "BLOCKING": [{"file": "...", "line": N, "pattern": "DROP COLUMN"}, ...], "WARN": [{"file": "...", "line": N, "pattern": "..."}, ...], "ACKNOWLEDGE": [{"file": "...", "line": N, "pattern": "...", "rationale": "..."}, ...] }, "user_acknowledgment": "string | null", "started_at": "ISO-8601", "completed_at": "ISO-8601" }

**MANDATORY: ⛔ Save state to file — Write tool → [state.state_path]**

### Step 12.0.5b Anti-Rationalization

| Rationalization | Why It's WRONG | Required Action |
| --- | --- | --- |
| "This migration looks simple, skip the check" | Simple migrations cause incidents too. Gate 0.5D only fires on BLOCKING patterns — if it fires, it's not simple. | **MUST run whenever migration files present in cycle diff.** |
| "ACKNOWLEDGE findings are informational, just log them" | ACKNOWLEDGE means the author MUST confirm intent. Silent acknowledgment is not acknowledgment. | **MUST pause cycle and require explicit user phrase.** |
| "Gate 0.5D and Gate 0.5G are redundant" | Different domains: 0.5G = multi-tenant Go code safety; 0.5D = SQL schema evolution safety. Orthogonal. | **MUST run both gates; they check different properties.** |
| "Delivery-verification already covers migrations at Gate 0" | Gate 0's delivery verification is per-subtask on application code, not cycle-wide SQL. Cycle-level diff can only be assessed post-cycle. | **MUST run 0.5D post-cycle on the full cycle diff.** |
| "Migration was in an early task, already committed per-task" | 0.5D inspects cumulative cycle diff vs origin/main. Per-task commits don't exempt cycle-level safety. | **MUST check against origin/main, not per-task boundary.** |
| "BLOCKING will cause rework, let's downgrade to WARN" | Severity is set by migration-safety.md. Downgrading violates the standard. | **MUST HARD BLOCK on BLOCKING; use ACKNOWLEDGE only for documented expand-contract.** |

---

### Step 12.1: Final Commit

1. **FINAL COMMIT CHECK (before completion):**
  - if `commit_timing == "at_end"`:
    - Execute `/ring:commit` command with message: `feat({cycle_id}): complete dev cycle for {feature_name}`
    - Include all changed files from the entire cycle
  - else: Already committed per subtask or per task
2. **Calculate metrics:** total_duration_ms, average gate durations, review iterations, pass/fail ratio
3. **Update state:** `status = "completed"`, `completed_at = timestamp`
4. **Generate report:** Task | Subtasks | Duration | Review Iterations | Status | Commit Status
5. **⛔ MANDATORY: Run ring:dev-report skill for cycle metrics** **IMPORTANT:** This is the ONE AND ONLY ring:dev-report dispatch in the cycle. ring:dev-report reads `accumulated_metrics` from ALL tasks in state and generates aggregate analysis. `Skill tool: skill: "ring:dev-report"` **Note:** ring:dev-report manages its own TodoWrite tracking internally. **After feedback-loop completes, update state:** **⛔ HARD GATE: Cycle incomplete until feedback-loop executes.** Rationalization Why It's WRONG Required Action "Cycle done, feedback is extra" Feedback IS part of cycle completion **Execute Skill tool** "Will run feedback next session" Next session = never. Run NOW. **Execute Skill tool** "All tasks passed, no insights" Pass patterns need documentation too **Execute Skill tool**
  - Set `feedback_loop_completed = true` at cycle level in state file
6. **Report:** "Cycle completed. Tasks X/X, Subtasks Y, Time Xh Xm, Review iterations X"

## Quick Commands

Full PM workflow then dev execution

/ring:pre-dev-full my-feature /ring:dev-cycle docs/pre-dev/my-feature/

Simple PM workflow then dev execution

/ring:pre-dev-feature my-feature /ring:dev-cycle docs/pre-dev/my-feature/tasks.md

Manual task file

/ring:dev-cycle docs/tasks/sprint-001.md

Resume interrupted cycle

/ring:dev-cycle --resume

## Error Recovery

| Type | Condition | Action |
| --- | --- | --- |
| **Recoverable** | Network timeout | Retry with exponential backoff |
| **Recoverable** | Agent failure | Retry once, then pause for user |
| **Recoverable** | Test flakiness | Re-run tests up to 2 times |
| **Non-Recoverable** | Missing required files | Stop and report |
| **Non-Recoverable** | Invalid state file | Must restart (cannot resume) |
| **Non-Recoverable** | Max review iterations | Pause for user |

**On any error:** Update state → Set status (failed/paused) → Save immediately → Report (what failed, why, how to recover, resume command)

## Execution Report

Base metrics per [shared-patterns/output-execution-report.md](https://github.com/lerianstudio/ring/blob/HEAD/dev-team/skills/dev-cycle/../shared-patterns/output-execution-report.md).

| Metric | Value |
| --- | --- |
| Duration | Xh Xm Ys |
| Tasks Processed | N/M |
| Current Gate | Gate X - [name] |
| Review Iterations | N |
| Result | PASS/FAIL/IN_PROGRESS |

### Gate Timings

| Gate | Duration | Status |
| --- | --- | --- |
| Implementation | Xm Ys | in_progress |
| DevOps | - | pending |
| SRE | - | pending |
| Testing | - | pending |
| Review | - | pending |
| Validation | - | pending |

### State File Location

`docs/ring:dev-cycle/current-cycle.json` (feature) or `docs/ring:dev-refactor/current-cycle.json` (refactor)

---

## Frontend Handoff

When the backend dev cycle completes, it produces a handoff file for the frontend dev cycle (`ring:dev-cycle-frontend`). This enables the frontend cycle to verify E2E tests exercise the correct API endpoints and use the right type contracts.

### Handoff File

**Path:** `docs/ring:dev-cycle/handoff-frontend.json`

**Generated:** Automatically after Gate 9 (Validation) passes for all tasks.

### Handoff Schema

{ "cycle_id": "string", "generated_at": "ISO-8601", "endpoints": [ { "method": "GET|POST|PUT|PATCH|DELETE", "path": "/api/v1/resource", "request_schema": "object or null", "response_schema": "object", "status_codes": [200, 400, 404, 500], "auth_required": true } ], "types_exported": [ { "name": "ResourceDTO", "file": "src/types/resource.ts", "fields": ["id", "name", "createdAt"] } ], "contracts": [ { "consumer": "frontend", "provider": "backend", "endpoint": "/api/v1/resource", "format": "JSON" } ] }

### How Frontend Cycle Uses the Handoff

| Frontend Gate | Handoff Usage |
| --- | --- |
| Gate 0 (Implementation) | Import types from `types_exported`, call `endpoints` |
| Gate 5 (E2E Testing) | Verify all `endpoints` are exercised in E2E tests |
| Gate 6 (Performance) | Measure response times against `endpoints` |

### When No Handoff Exists

If `docs/ring:dev-cycle/handoff-frontend.json` does not exist, the frontend cycle proceeds without it. The frontend engineer defines API contracts inline based on `PROJECT_RULES.md` or user input. This is common for greenfield frontend-only projects.