Skip to content
FunCoding

Search

Search docs, Skills and MCP

debug-hooks

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

代码质量与审查3.9k.claude/skills/debug-hooks/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/parcadei/continuous-claude-v3/debug-hooks/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Debug Hooks

Systematic workflow for debugging Claude Code hooks.

When to Use

  • "Hook isn't firing"
  • "Hook produces wrong output"
  • "SessionEnd not working"
  • "PostToolUse hook not triggering"
  • "Why didn't my hook run?"

Workflow

1. Check Outputs First (Observe Before Editing)

# Check project cache
ls -la $CLAUDE_PROJECT_DIR/.claude/cache/

# Check specific outputs
ls -la $CLAUDE_PROJECT_DIR/.claude/cache/learnings/

# Check for debug logs
tail $CLAUDE_PROJECT_DIR/.claude/cache/*.log 2>/dev/null

# Also check global (common mistake: wrong path)
ls -la ~/.claude/cache/ 2>/dev/null

2. Verify Hook Registration

# Project settings
cat $CLAUDE_PROJECT_DIR/.claude/settings.json | grep -A 20 '"SessionEnd"\|"PostToolUse"\|"UserPromptSubmit"'

# Global settings (hooks merge from both)
cat ~/.claude/settings.json | grep -A 20 '"SessionEnd"\|"PostToolUse"\|"UserPromptSubmit"'

3. Check Hook Files Exist

# Shell wrappers
ls -la $CLAUDE_PROJECT_DIR/.claude/hooks/*.sh

# Compiled bundles (if using TypeScript)
ls -la $CLAUDE_PROJECT_DIR/.claude/hooks/dist/*.mjs

4. Test Hook Manually

# SessionEnd hook
echo '{"session_id": "test-123", "reason": "clear", "transcript_path": "/tmp/test"}' | \
  $CLAUDE_PROJECT_DIR/.claude/hooks/session-end-cleanup.sh

# PostToolUse hook (Write tool example)
echo '{"tool_name": "Write", "tool_input": {"file_path": "test.md"}, "session_id": "test-123"}' | \
  $CLAUDE_PROJECT_DIR/.claude/hooks/handoff-index.sh

5. Check for Silent Failures

If using detached spawn with stdio: 'ignore':

// This pattern hides errors!
spawn(cmd, args, { detached: true, stdio: 'ignore' })

Fix: Add temporary logging:

const logFile = fs.openSync('.claude/cache/debug.log', 'a');
spawn(cmd, args, {
  detached: true,
  stdio: ['ignore', logFile, logFile]  // capture stdout/stderr
});

6. Rebuild After Edits

If you edited TypeScript source, you MUST rebuild:

cd $CLAUDE_PROJECT_DIR/.claude/hooks
npx esbuild src/session-end-cleanup.ts \
  --bundle --platform=node --format=esm \
  --outfile=dist/session-end-cleanup.mjs

Source edits alone don't take effect - the shell wrapper runs the bundled .mjs.

Common Issues

SymptomLikely CauseFix
Hook never runsNot registered in settings.jsonAdd to correct event in settings
Hook runs but no outputDetached spawn hiding errorsAdd logging, check manually
Wrong session IDUsing "most recent" queryPass ID explicitly
Works locally, not in CIMissing dependenciesCheck npx/node availability
Runs twiceRegistered in both global + projectRemove duplicate

Debug Checklist

  • Outputs exist? (ls -la .claude/cache/)
  • Registered? (grep -A10 '"hooks"' .claude/settings.json)
  • Files exist? (ls .claude/hooks/*.sh)
  • Bundle current? (ls -la .claude/hooks/dist/)
  • Manual test works? (echo '{}' | ./hook.sh)
  • No silent failures? (check for stdio: 'ignore')

Source Sessions

Derived from 10 sessions (83% of all learnings):

  • a541f08a, 1c21e6c8, 6a9f2d7a, a8bd5cea, 2ca1a178, 657ce0b2, 3998f3a2, 2a829f12, 0b46cfd7, 862f6e2c

Similar Skills

claude-api
anthropics/skills180k

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

Code quality & review

ponytail-review
DietrichGebert/ponytail158k

ponytail-review

Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for "review this", "code review", "review the last commit", "review my PR", "is this over-engineered", /ponytail-review.

Code quality & review

code-review-and-quality
addyosmani/agent-skills103k

code-review-and-quality

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when the diff is pasted inline.

Code quality & review

documentation-and-adrs
addyosmani/agent-skills103k

documentation-and-adrs

Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Code quality & review

code-simplification
addyosmani/agent-skills103k

code-simplification

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Code quality & review

understand
Egonex-AI/Understand-Anything86k

understand

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

Code quality & review