code-auto（自动代码）

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

AI Mistake Prevention — Failure modes to avoid on every task: - Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. - Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. - Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. - Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. - When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. - Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. - Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. - Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. - Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. - Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Understand Code First — HARD-GATE: Do NOT write, plan, or fix until you READ existing code. 1. Search 3+ similar patterns (grep/glob) — cite file:line evidence 2. Read existing files in target area — understand structure, base classes, conventions 3. Run python.claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists 4. Map dependencies via connections or callers_of — know what depends on your target 5. Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files) 6. Re-read analysis file before implementing — never work from memory alone 7. NEVER invent new patterns when existing ones work — match exactly or document deviation BLOCKED until: - [] Read target files - [] Grep 3+ patterns - [] Graph trace (if graph.db exists) - [] Assumptions verified with evidence

• docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models) (content auto-injected by hook — check for [Injected:...] header before reading)

Quick Summary

Goal: Automatically execute an existing plan with testing and code review — no user approval gate (trust mode).

Workflow:

1. Plan Detection — Find latest plan or use provided path, select next incomplete phase
2. Analysis & Tasks — Extract tasks into TaskCreate with step numbering
3. Implementation — Implement phase step-by-step, run type checks
4. Testing — Tester subagent; must reach 100% pass
5. Code Review — Code-reviewer subagent; must reach 0 critical issues
6. Finalize — Update status, docs, auto-commit; optionally loop to next phase

Key Rules:

• No user approval gate (unlike /code which has a blocking Step 5)
• Tests must be 100% passing; critical issues must be 0
• $ALL_PHASES=Yes (default) processes all phases in one run
• Never comment out tests or use fake data to pass

MUST ATTENTION READ CLAUDE.md then THINK HARDER to start working on the following plan:

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

$ARGUMENTS

Arguments

• $PLAN: $1 (Mention specific plan or auto detected, default: latest plan)
• $ALL_PHASES: $2 (Yes to finish all phases in one run or No to implement phase-by-phase, default: Yes)

Step 0: Plan Detection & Phase Selection

If $PLAN is empty:

1. Find latest plan.md in ./plans
2. Parse plan for phases and status, auto-select next incomplete

If $PLAN provided: Use that plan and detect which phase to work on.

Output: ✓ Step 0: [Plan Name] - [Phase Name]

Workflow Sequence

Rules: Follow steps 1-5 in order. Each step requires output marker ✓ Step N:. Mark each complete in TaskCreate before proceeding. Do not skip steps.

Step 1: Analysis & Task Extraction

Use project-manager agent to read plan file completely. Map dependencies. List ambiguities. Identify required skills. If the plan references analysis files in .ai/workspace/analysis/, re-read them before implementation.

TaskCreate Initialization:

• Initialize TaskCreate with Step 0: [Plan Name] - [Phase Name] and all steps (1-5)
• Read phase file, look for tasks/steps/phases/sections/numbered/bulleted lists
• Convert to TaskCreate tasks with UNIQUE names:

- Phase Implementation tasks → Step 2.X (Step 2.1, Step 2.2, etc.) - Phase Testing tasks → Step 3.X - Phase Code Review tasks → Step 4.X

Output: ✓ Step 1: Found [N] tasks across [M] phases - Ambiguities: [list or "none"]

Step 2: Implementation

Implement selected plan phase step-by-step. Mark tasks complete as done. For UI work, call ui-ux-designer subagent. Run type checking and compile.

Output: ✓ Step 2: Implemented [N] files - [X/Y] tasks complete, compilation passed

Step 3: Testing

Call tester subagent. If ANY tests fail: STOP, call debugger, fix, re-run. Repeat until 100% pass.

Testing standards: Forbidden: commenting out tests, changing assertions to pass, TODO/FIXME to defer fixes.

Output: ✓ Step 3: Tests [X/X passed] - All requirements met

Validation: If X ≠ total, Step 3 INCOMPLETE - do not proceed.

Step 4: Code Review

Call code-reviewer subagent. If critical issues found: STOP, fix, re-run tester, re-run code-reviewer. Repeat until no critical issues.

Output: ✓ Step 4: Code reviewed - [0] critical issues

Validation: If critical issues > 0, Step 4 INCOMPLETE - do not proceed.

Step 5: Finalize

1. STATUS UPDATE (PARALLEL): Call project-manager + docs-manager subagents.
2. ONBOARDING CHECK: Detect onboarding requirements + generate summary.
3. AUTO-COMMIT: Call git-manager subagent. Run only if Steps 1-2 successful + Tests passed.

If $ALL_PHASES is Yes: proceed to next phase automatically. If $ALL_PHASES is No: ask user before proceeding to next phase.

If last phase: Generate summary report. Ask user about /preview and /plan-archive.

Output: ✓ Step 5: Finalize - Status updated - Git committed

Critical Enforcement Rules

Step output format: ✓ Step [N]: [Brief status] - [Key metrics]

TaskCreate tracking required: Initialize at Step 0, mark each step complete before next.

Mandatory subagent calls: Step 3: tester | Step 4: code-reviewer | Step 5: project-manager AND docs-manager AND git-manager

Blocking gates:

• Step 3: Tests must be 100% passing
• Step 4: Critical issues must be 0

Do not skip steps. Do not proceed if validation fails. One plan phase per command run.

Next Steps (Standalone: MUST ATTENTION ask user via AskUserQuestion. Skip if inside workflow.)

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS: If this skill was called outside a workflow, you MUST ATTENTION use AskUserQuestion to present these options. Do NOT skip because the task seems "simple" or "obvious" — the user decides:

• "Proceed with full workflow (Recommended)" — I'll detect the best workflow to continue from here (code implemented). This ensures review, testing, and docs steps aren't skipped.
• "/code-simplifier" — Simplify implementation
• "/workflow-review-changes" — Review changes before commit
• "Skip, continue manually" — user decides

If already inside a workflow, skip — the workflow handles sequencing.

Closing Reminders

• IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
• IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
• IMPORTANT MUST ATTENTION add a final review todo task to verify work quality
• IMPORTANT MUST ATTENTION validate decisions with user via AskUserQuestion — never auto-decide MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:
• IMPORTANT MUST ATTENTION search 3+ existing patterns and read code BEFORE any modification. Run graph trace when graph.db exists.
• IMPORTANT MUST ATTENTION READ CLAUDE.md before starting
• MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.
• MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.