fix-issue（解决问题）

Fix Issue

Systematic issue resolution with hypothesis-based root cause analysis, similar issue detection, and prevention recommendations.

Quick Start

/ork:fix-issue 123
/ork:fix-issue 456

Opus 4.6: Root cause analysis uses native adaptive thinking. Dynamic token budgets scale with context window for thorough investigation.

CC ≥ 2.1.119 multi-host note (M122): Issue fetching works against GitHub, GitLab, Bitbucket, and GitHub Enterprise. The argument is either a numeric ID (use the configured default remote's host) or a full URL (parsed via parsePrUrl/parseIssueUrl from src/hooks/src/lib/pr-host-parser.ts). Branch on the detected host family for the right CLI: gh issue view (GitHub/GHE), glab issue view (GitLab), bb issue view (Bitbucket). Reference: src/skills/chain-patterns/references/pr-from-platform.md.

Argument Resolution

ISSUE_NUMBER = "$ARGUMENTS[0]"  # e.g., "123" (CC 2.1.59 indexed access)
# $ARGUMENTS contains the full argument string
# $ARGUMENTS[0] is the first space-separated token

STEP -1: MCP Probe + Resume Check

Run BEFORE any other step. Detect available MCP servers and check for resumable state.

# Probe MCPs (parallel — all in ONE message):
# memory is alwaysLoad in .mcp.json (CC 2.1.121+, #1541) — probe below kept as fallback for older CC:
ToolSearch(query="select:mcp__memory__search_nodes")
ToolSearch(query="select:mcp__context7__resolve-library-id")

# Write capability map:
Write(".claude/chain/capabilities.json", JSON.stringify({
  "memory": <true if found>,
  "context7": <true if found>,
  "timestamp": now()
}))

# Check for resumable state:
Read(".claude/chain/state.json")
# If exists and skill == "fix-issue":
#   Read last handoff, skip to current_phase
#   Tell user: "Resuming from Phase {N}"
# If not exists: write initial state
Write(".claude/chain/state.json", JSON.stringify({
  "skill": "fix-issue",
  "issue": ISSUE_NUMBER,
  "current_phase": 1,
  "completed_phases": [],
  "capabilities": capabilities
}))

Load pattern details: Read("${CLAUDE_PLUGIN_ROOT}/skills/chain-patterns/references/mcp-detection.md")

CRITICAL: Task Management is MANDATORY (CC 2.1.16)

BEFORE doing ANYTHING else (after MCP probe), create tasks to track progress:

# 1. Create main task IMMEDIATELY
TaskCreate(
  subject="Fix Issue: #{ISSUE_NUMBER}",
  description="Systematic issue resolution with RCA and prevention",
  activeForm="Fixing issue #{ISSUE_NUMBER}"
)

# 2. Create subtasks for each key phase
TaskCreate(subject="Understand issue", activeForm="Reading issue details")
TaskCreate(subject="Hypothesis & RCA", activeForm="Analyzing root cause")
TaskCreate(subject="Implement fix", activeForm="Applying fix with tests")
TaskCreate(subject="Validate & prevent", activeForm="Validating fix and prevention")
TaskCreate(subject="Commit and PR", activeForm="Creating PR for fix")

# 3. Set dependencies for sequential phases
TaskUpdate(taskId="3", addBlockedBy=["2"])
TaskUpdate(taskId="4", addBlockedBy=["3"])
TaskUpdate(taskId="5", addBlockedBy=["4"])
TaskUpdate(taskId="6", addBlockedBy=["5"])

# 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

STEP 0: Effort-Aware Fix Scaling (CC 2.1.76)

Scale investigation depth based on /effort level:

Override: Explicit user selection (e.g., "Proper fix") overrides /effort downscaling. Hotfix always uses minimal phases regardless of effort.

STEP 0a: Verify User Intent

BEFORE creating tasks, clarify fix approach:

AskUserQuestion(
  questions=[{
    "question": "How do you want to approach this fix?",
    "header": "Fix Approach",
    "options": [
      {"label": "Proper fix (Recommended)", "description": "Full RCA, regression test, prevention plan", "markdown": "```\nProper Fix (11 phases)\n──────────────────────\n  Understand ──▶ Hypothesize ──▶ RCA\n       │              │           │\n       ▼              ▼           ▼\n  5 parallel     Ranked       Confirmed\n  agents         hypotheses   root cause\n       │\n       ▼\n  Fix ──▶ Validate ──▶ Prevent ──▶ PR\n  + regression test   + runbook\n```"},
      {"label": "Quick fix", "description": "Minimal investigation, fix and test", "markdown": "```\nQuick Fix (~10 min)\n───────────────────\n  Read issue ──▶ Fix ──▶ Test ──▶ PR\n\n  Skip: full RCA, prevention plan,\n  runbook, lessons learned\n  Keep: regression test (mandatory)\n```"},
      {"label": "Investigate first", "description": "Deep analysis before deciding on approach", "markdown": "```\nInvestigate First\n─────────────────\n  Read issue ──▶ 5 parallel agents ──▶ Report\n\n  Output: Root cause analysis\n  + hypothesis ranking\n  + recommended approach\n  No code changes yet\n```"},
      {"label": "Hotfix", "description": "Emergency fix, minimal process", "markdown": "```\nHotfix (emergency)\n──────────────────\n  Read issue ──▶ Fix ──▶ Push\n\n  Skip: agents, RCA, prevention\n  Keep: basic test verification\n  Post-fix: schedule proper RCA\n```"}
    ],
    "multiSelect": false
  }]
)

Based on answer, adjust workflow:

• Proper fix: All 11 phases, 5 parallel RCA agents
• Quick fix: Phases 1, 6, 7, 11 only — skip RCA agents and prevention
• Investigate first: Enter plan mode for read-only analysis, then decide
• Hotfix: Phases 1, 6, 11 only — emergency path

Sub-question: Local-CI Strategy (AskUserQuestion — M118 #1467)

Once the approach is chosen, ask whether to run CI locally before pushing — orthogonal to fix depth:

# Skip when invocation flag is explicit:
#   /ork:fix-issue 123 --local-ci          → skip, run full suite locally
#   /ork:fix-issue 123 --security-only     → skip, security tests only
#   /ork:fix-issue 123 --push-and-let-ci   → skip, no local run
#
# Force local-CI when issue has security or data-loss labels (warns user it overrode their choice).

AskUserQuestion(questions=[{
  "question": "Before push?",
  "header": "Local CI",
  "options": [
    {"label": "Push and let CI run (default)", "description": "Fastest round-trip, CI catches failures"},
    {"label": "Run full suite locally first", "description": "~2-3 min extra; catches CI failures locally before push"},
    {"label": "Run security tests only", "description": "~30s; covers the usual blocker class — secrets, deps, common vulns"}
  ]
}])

Override rule: if the issue's GitHub labels include security or data-loss, override the user's selection with "Run full suite locally first" and surface a one-line notification: *"Security/data-loss label detected — running full local suite as a precaution."* The user can still bypass with the --push-and-let-ci arg, which logs the bypass for audit.

If 'Investigate first' selected:

# 1. Enter read-only plan mode
EnterPlanMode("Investigate issue: $ISSUE_REF")

# 2. Investigation phase — Read/Grep/Glob ONLY, no Write/Edit
#    - Read the issue description and linked context
#    - Trace the error path through relevant code
#    - Search for related issues, past fixes, test failures
#    - Build hypothesis list with evidence

# 3. Produce RCA report:
#    - Root cause hypothesis (ranked by confidence)
#    - Affected files and blast radius
#    - Recommended approach (proper fix vs quick fix)
#    - Risk assessment

# 4. Exit plan mode — returns analysis for user decision
ExitPlanMode()

# 5. User reviews RCA. If "proceed with fix" → continue to Phase 5 (Fix).
#    If "need more info" → re-enter investigation.

Load Read("${CLAUDE_SKILL_DIR}/rules/evidence-gathering.md") for detailed workflow adjustments per approach.

STEP 0b: Select Orchestration Mode

Choose Agent Teams (mesh) or Task tool (star). Load Read("${CLAUDE_SKILL_DIR}/references/agent-selection.md") for the selection criteria, cost comparison, and task creation patterns.

Service Discovery & Visual Inspection

When the issue involves a running web app, API, or UI bug, discover services and inspect visually before forming hypotheses:

# 1. Discover services via Portless (preferred)
portless list 2>/dev/null
# api → api.localhost:1355   (port 8080)
# app → app.localhost:1355   (port 3000)

# 2. Fallback: discover ports manually
lsof -iTCP -sTCP:LISTEN -nP | grep -E 'node|python|java'

# 3. Visual inspection with agent-browser
agent-browser open "http://app.localhost:1355"
agent-browser screenshot /tmp/issue-before.png     # capture broken state
agent-browser console                              # check for JS errors
agent-browser network log                          # inspect failed API calls
agent-browser get text @error-banner               # extract error messages

Use Portless named URLs (*.localhost:1355) in all investigation steps — they're stable, self-documenting, and eliminate port-guessing failures. Install with npm i -g portless.

Workflow Overview

Progressive Output (CC 2.1.76)

Output results incrementally as each phase completes — don't batch until the PR:

For the proper fix path with 5 parallel RCA agents, output each agent's findings as they return — don't wait for all 5. If one agent identifies the root cause with high confidence early, flag it immediately so the user can confirm and skip remaining agents.

Phase Handoffs (CC 2.1.71)

Write handoff JSON after phases 3, 4, 6, 7 to .claude/chain/. See chain-patterns skill for schema.

Worktree-Isolated RCA Agents (CC 2.1.50)

Phase 4 agents SHOULD use isolation: "worktree" when they need to edit files:

Agent(subagent_type="debug-investigator",
  prompt="Investigate hypothesis: {desc}...",
  isolation="worktree", run_in_background=true)

Post-Fix Monitoring (CC 2.1.71)

After Phase 11 (commit + PR), schedule CI monitoring:

# Guard: Skip cron in headless/CI (CLAUDE_CODE_DISABLE_CRON)
# if env CLAUDE_CODE_DISABLE_CRON is set, run a single check instead
CronCreate(
  schedule="*/5 * * * *",
  prompt="Check CI for PR #{pr_number}: gh pr checks {pr_number} --repo {repo}.
    All pass → CronDelete this job. Any fail → alert with details."
)

Worktree Cleanup (CC 2.1.72)

If worktree isolation was used in Phase 4, clean up after validation:

# After Phase 7 validation passes — exit worktree, keep branch for PR
ExitWorktree(action="keep")

Every EnterWorktree or isolation: "worktree" agent must have a matching cleanup. If agents used isolation: "worktree", they handle their own exit — but if the lead entered a worktree in Step 0, it must call ExitWorktree before Phase 11 commit.

Fix Pattern Memory

If memory MCP is available (from Step -1 probe), save the fix pattern:

if capabilities.memory:
  mcp__memory__create_entities([{
    name: "fix-pattern-{slug}",
    entityType: "fix-pattern",
    observations: [root_cause, fix_description, regression_test, issue_ref]
  }])

Full phase details: Load Read("${CLAUDE_SKILL_DIR}/references/fix-phases.md") for bash commands, templates, and procedures for each phase.

Critical Constraints

• Feature branch MANDATORY -- NEVER commit directly to main or dev
• Regression test MANDATORY -- write failing test BEFORE implementing fix
• Prevention required -- at least one of: automated test, validation rule, or process check
• Make minimal, focused changes; DO NOT over-engineer

CC 2.1.49 Enhancements

Load Read("${CLAUDE_SKILL_DIR}/references/cc-enhancements.md") for session resume, task metrics, tool guidance, worktree isolation, and adaptive thinking.

Rules Quick Reference

Push notifications (CC 2.1.110+): Issue-fix flows can span 10–20 min with RCA → fix → test → PR. When the fix lands and tests pass, call PushNotification so the user knows the fix is ready for review. Requires Remote Control + "Push when Claude decides" config; fails silently if unavailable. ``python PushNotification( title="ork:fix-issue complete", body=f"#{issue_number}: fix pushed, {tests_passing}/{tests_total} tests · PR #{pr_number}" ) ``

Agent Coordination

SendMessage (Evidence Sharing)

When an RCA agent discovers the root cause, share with the fix agent:

SendMessage(to="debug-investigator", message="Root cause: race condition in cache invalidation — see git blame for commit abc123")

Context Passing

All 5 RCA agents receive: issue description, ranked hypotheses, reproduction steps, and affected file paths — not just "investigate issue #N".

Skill Chain

After fix is applied: TaskCreate(subject="Verify fix", addBlockedBy=[fix_task_id]) → /ork:verify.

Verification Gate

Before claiming any fix is complete, apply the 5-step verification gate: Read("${CLAUDE_PLUGIN_ROOT}/skills/shared/rules/verification-gate.md"). "Should work now" is not evidence — run the test, read the output, cite the result.

Response Protocol

When reporting fix status, follow Read("${CLAUDE_PLUGIN_ROOT}/skills/shared/rules/anti-sycophancy.md") — state findings directly, no performative language. Use the agent status protocol: DONE, DONE_WITH_CONCERNS, BLOCKED, or NEEDS_CONTEXT.

Related Skills

• ork:commit - Commit issue fixes
• debug-investigator - Debug complex issues
• browser-tools - Visual inspection with agent-browser + Portless
• ork:issue-progress-tracking - Auto-updates from commits
• ork:remember - Store lessons learned

Session recovery (CC 2.1.108+): After idle periods or interruptions, use /recap to restore conversational context alongside checkpoint-resume state. Enabled by default since CC 2.1.110 (even with telemetry disabled).

References

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

Version: 2.4.0 (March 2026) — Rich elicitation with options for fix approach, progressive output for incremental phase results