visualize-plan（可视化计划）

Plan Visualization

Render planned changes as structured ASCII visualizations with risk analysis, execution order, and impact metrics. Every section answers a specific reviewer question.

Core principle: Encode judgment into visualization, not decoration.

/ork:visualize-plan                          # Auto-detect from current branch
/ork:visualize-plan billing module redesign  # Describe the plan
/ork:visualize-plan #234                     # Pull from GitHub issue

Argument Resolution

PLAN_INPUT = "$ARGUMENTS"    # Full argument string
PLAN_TOKEN = "$ARGUMENTS[0]" # First token — could be issue "#234" or plan description
# If starts with "#", treat as GitHub issue number. Otherwise, plan description.
# $ARGUMENTS (full string) for multi-word descriptions (CC 2.1.59 indexed access)

CRITICAL: Task Tracking

# 1. Create main task IMMEDIATELY
TaskCreate(subject="Visualize plan: {PLAN_INPUT}", description="Plan visualization with ASCII rendering", activeForm="Analyzing plan context")

# 2. Create subtasks for each phase
TaskCreate(subject="Detect or clarify plan context", activeForm="Detecting plan context")          # id=2
TaskCreate(subject="Gather data and explore architecture", activeForm="Gathering plan data")       # id=3
TaskCreate(subject="Render tier 1 header", activeForm="Rendering header")                          # id=4
TaskCreate(subject="Render requested sections", activeForm="Rendering sections")                   # id=5
TaskCreate(subject="Offer actions and store in memory", activeForm="Finalizing visualization")     # id=6

# 3. Set dependencies for sequential phases
TaskUpdate(taskId="3", addBlockedBy=["2"])  # Data gathering needs context first
TaskUpdate(taskId="4", addBlockedBy=["3"])  # Header needs gathered data
TaskUpdate(taskId="5", addBlockedBy=["4"])  # Sections need header rendered
TaskUpdate(taskId="6", addBlockedBy=["5"])  # Actions need sections done

# 4. Before starting each task, verify it's unblocked
task = TaskGet(taskId="2")  # Verify blockedBy is empty

# 5. Update status as you progress
TaskUpdate(taskId="2", status="in_progress")  # When starting
TaskUpdate(taskId="2", status="completed")    # When done — repeat for each subtask

STEP -1: Check Memory for Prior Plans

# Search for related prior visualizations
mcp__memory__search_nodes(query="plan visualization {PLAN_INPUT}")
# If found, offer to compare with previous plan

STEP 0: Detect or Clarify Plan Context

First, attempt auto-detection by running scripts/detect-plan-context.sh:

bash "$SKILL_DIR/scripts/detect-plan-context.sh"

This outputs branch name, issue number (if any), commit count, and file change summary.

If auto-detection finds a clear plan (branch with commits diverging from main, or issue number in args), proceed to Step 1.

If ambiguous, clarify with AskUserQuestion:

AskUserQuestion(
  questions=[{
    "question": "What should I visualize?",
    "header": "Source",
    "options": [
      {"label": "Current branch changes (Recommended)", "description": "Auto-detect from git diff against main", "markdown": "```\nBranch Diff Analysis\n────────────────────\n$ git diff main...HEAD\n\n→ File change manifest (+A, M, -D)\n→ Execution swimlane by phase\n→ Risk dashboard + pre-mortems\n→ Impact summary (lines, tests, API)\n```"},
      {"label": "Describe the plan", "description": "I'll explain what I'm planning to change", "markdown": "```\nPlan Description\n────────────────\nYou describe → I visualize:\n\n→ Before/after architecture diagrams\n→ Execution order with dependencies\n→ Risk analysis per component\n→ Decision log (ADR-lite format)\n```"},
      {"label": "GitHub issue", "description": "Pull plan from a specific issue number", "markdown": "```\nGitHub Issue Source\n───────────────────\n$ gh issue view #N\n\n→ Extract requirements from body\n→ Map to file-level changes\n→ Generate execution phases\n→ Link back to issue for tracking\n```"},
      {"label": "Quick file diff only", "description": "Just show the change manifest, skip analysis", "markdown": "```\nQuick File Diff\n───────────────\n[A] src/new-file.ts        +120\n[M] src/existing.ts    +15  -8\n[D] src/old-file.ts        -45\n─────────────────────────────\nNET: +82 lines, 3 files\n\nNo risk analysis or swimlanes\n```"}
    ],
    "multiSelect": false
  }]
)

STEP 1: Gather Data

Run scripts/analyze-impact.sh for precise counts:

bash "$SKILL_DIR/scripts/analyze-impact.sh"

This produces: files by action (add/modify/delete), line counts, test files affected, and dependency changes.

For architecture-level understanding, spawn an Explore agent on the affected directories:

Agent(
  subagent_type="Explore",
  prompt="Explore the architecture of {affected_directories}. Return: component diagram, key data flows, health scores per module. Use the ascii-visualizer skill for diagrams.",
  model="haiku"
)

STEP 2: Render Tier 1 Header (Always)

Use assets/tier1-header.md template. Load Read("${CLAUDE_SKILL_DIR}/references/visualization-tiers.md") for field computation (risk level, confidence, reversibility).

PLAN: {plan_name} ({issue_ref})  |  {phase_count} phases  |  {file_count} files  |  +{added} -{removed} lines
Risk: {risk_level}  |  Confidence: {confidence}  |  Reversible until {last_safe_phase}
Branch: {branch} -> {base_branch}

[1] Changes  [2] Execution  [3] Risks  [4] Decisions  [5] Impact  [all]

STEP 3: Ask Which Sections to Expand

AskUserQuestion(
  questions=[{
    "question": "Which sections to render?",
    "header": "Sections",
    "options": [
      {"label": "All sections", "description": "Full visualization with all 5 core sections", "markdown": "```\n[1] Change Manifest   [A]/[M]/[D] file tree\n[2] Execution         Swimlane with phases\n[3] Risks             Dashboard + pre-mortems\n[4] Decisions         ADR-lite decision log\n[5] Impact            Lines, tests, API, deps\n```"},
      {"label": "Changes + Execution", "description": "File diff tree and execution swimlane", "markdown": "```\n[1] Change Manifest\n    [M] src/auth.ts         +45 -12\n    [A] src/oauth.ts        +89\n\n[2] Execution Swimlane\n    Phase 1 ====[auth]========▶\n    Phase 2 ----[blocked]--===▶\n```"},
      {"label": "Risks + Decisions", "description": "Risk dashboard and decision log", "markdown": "```\n[3] Risk Dashboard\n    MEDIUM ██░░ migration reversible\n    HIGH   ███░ API breaking change\n    Pre-mortem: \"What if auth fails?\"\n\n[4] Decision Log\n    D1: OAuth2 over JWT (security)\n    D2: Postgres over Redis (durability)\n```"},
      {"label": "Impact only", "description": "Just the numbers: files, lines, tests, API surface", "markdown": "```\n[5] Impact Summary\n    ┌──────────┬─────┬───────┐\n    │ Metric   │Count│ Delta │\n    ├──────────┼─────┼───────┤\n    │ Files    │  12 │  +3   │\n    │ Lines    │ 450 │ +127  │\n    │ Tests    │   8 │  +4   │\n    │ API sfc  │   3 │  +1   │\n    └──────────┴─────┴───────┘\n```"}
    ],
    "multiSelect": false
  }]
)

STEP 4: Render Requested Sections

Render each requested section following ${CLAUDE_SKILL_DIR}/rules/section-rendering.md conventions. Use the corresponding reference for ASCII patterns:

STEP 5: Offer Actions

After rendering, offer next steps:

AskUserQuestion(
  questions=[{
    "question": "What next?",
    "header": "Actions",
    "options": [
      {"label": "Write to designs/", "description": "Save as designs/{branch}.md for PR review", "markdown": "```\nSave to File\n────────────\ndesigns/\n  └── feat-billing-redesign.md\n      ├── Header + metadata\n      ├── All rendered sections\n      └── Ready for PR description\n```"},
      {"label": "Generate GitHub issues", "description": "Create issues from execution phases with labels and milestones", "markdown": "```\nGitHub Issues\n─────────────\n#101 [billing] Phase 1: Schema migration\n     labels: component:billing, risk:medium\n#102 [billing] Phase 2: API endpoints\n     labels: component:billing, risk:low\n     blocked-by: #101\n```"},
      {"label": "Drill deeper", "description": "Expand blast radius, cross-layer check, or migration checklist", "markdown": "```\nDeep Dive Options\n─────────────────\n[6] Blast Radius\n    direct → transitive → test impact\n[7] Cross-Layer Consistency\n    Frontend ↔ Backend endpoint gaps\n[8] Migration Checklist\n    Ordered runbook with time estimates\n```"},
      {"label": "Done", "description": "Plan visualization complete"}
    ],
    "multiSelect": false
  }]
)

Write to file: Save full report to designs/{branch-name}.md using assets/plan-report.md template.

Generate issues: For each execution phase, create a GitHub issue with title [{component}] {phase_description}, labels (component + risk:{level}), milestone, body from plan sections, and blocked-by references.

Store in memory: Save plan summary to knowledge graph for future comparison:

mcp__memory__create_entities(entities=[{
  "name": "Plan: {plan_name}",
  "entityType": "plan-visualization",
  "observations": [
    "Branch: {branch}",
    "Risk: {risk_level}, Confidence: {confidence}",
    "Phases: {phase_count}, Files: {file_count}",
    "Key decisions: {decision_summary}"
  ]
}])

Deep Dives (Tier 3, on request)

Available when user selects "Drill deeper". Load Read("${CLAUDE_SKILL_DIR}/references/deep-dives.md") for cross-layer and migration patterns.

Key Principles

Rules Quick Reference

References

Load on demand with Read("${CLAUDE_SKILL_DIR}/references/<file>"):

Assets

Load on demand with Read("${CLAUDE_SKILL_DIR}/assets/<file>"):

Related Skills

• ork:implement - Execute planned changes
• ork:explore - Understand current architecture
• ork:assess - Evaluate complexity and risks
• ork:memory - Search prior plan visualizations
• ork:remember - Store plan decisions for future reference