📦 deps(thirdparty): update snapshots

This commit is contained in:
ci[bot]
2026-05-29 08:33:53 +00:00
parent fdb52f1e96
commit 06e0d13d57
1615 changed files with 232858 additions and 0 deletions
@@ -0,0 +1,486 @@
---
name: claude-hooks
description: This skill should be used when creating hooks, automating workflows, or when "PreToolUse", "PostToolUse", "hooks.json", "event handler", or "create hook" are mentioned.
metadata:
version: "2.0.0"
related-skills:
- claude-commands
- claude-plugins
- claude-agents
- claude-config
---
# Claude Hook Authoring
Create event hooks that automate workflows, validate operations, and respond to Claude Code events.
## Hook Types
Three hook execution types:
| Type | Best For | Example |
|------|----------|---------|
| **command** | Deterministic checks, external tools, performance | Bash script validates paths |
| **prompt** | Complex reasoning, context-aware validation | LLM evaluates if action is safe |
| **agent** | Multi-step verification requiring tool access | Agent with Read/Grep tools verifies consistency |
**Command hooks** (for deterministic/fast checks):
```json
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/validate.sh",
"timeout": 10
}
```
**Prompt hooks** (recommended for complex logic):
```json
{
"type": "prompt",
"prompt": "Evaluate if this file write is safe: $TOOL_INPUT. Check for sensitive paths, credentials, path traversal. Return 'allow' or 'deny' with reason.",
"timeout": 30
}
```
**Agent hooks** (for complex multi-step verification):
```json
{
"type": "agent",
"prompt": "Verify this code change maintains consistency with the existing codebase. Check imports, type signatures, and naming conventions. Use Read and Grep tools as needed.",
"allowedTools": ["Read", "Grep", "Glob"],
"timeout": 120
}
```
Agent hooks spawn a subagent with tool access for verification tasks that require reading files, searching code, or multi-step reasoning. Use when prompt hooks are insufficient.
## Hook Events
| Event | When | Can Block | Common Uses |
|-------|------|-----------|-------------|
| **PreToolUse** | Before tool executes | Yes | Validate commands, check paths, enforce policies |
| **PostToolUse** | After tool succeeds | No | Auto-format, run linters, update docs |
| **PostToolUseFailure** | After tool fails | No | Error logging, retry logic, notifications |
| **PermissionRequest** | Permission dialog shown | Yes | Auto-allow/deny based on rules |
| **UserPromptSubmit** | User submits prompt | No | Add context, log activity, augment prompts |
| **Notification** | Claude sends notification | No | External alerts, logging |
| **Stop** | Main agent finishes | No | Cleanup, completion notifications |
| **SubagentStart** | Subagent spawns | No | Track subagent usage |
| **SubagentStop** | Subagent finishes | No | Log results, trigger follow-ups |
| **Setup** | `--init`, `--init-only`, or `--maintenance` flags | No | Initialize environment, install dependencies |
| **PreCompact** | Before context compacts | No | Backup conversation, preserve context |
| **SessionStart** | Session starts/resumes | No | Load context, show status, init resources |
| **SessionEnd** | Session ends | No | Cleanup, save state, log metrics |
See [references/hook-types.md](references/hook-types.md) for detailed documentation of each event.
## Quick Start
### Auto-Format TypeScript
```json
{
"hooks": {
"PostToolUse": [
{
"matcher": "Write|Edit(*.ts|*.tsx)",
"hooks": [{
"type": "command",
"command": "biome check --write \"$file\"",
"timeout": 10
}]
}
]
}
}
```
### Block Dangerous Commands
```json
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/validate-bash.sh",
"timeout": 5
}]
}
]
}
}
```
**validate-bash.sh**:
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command // empty')
if echo "$COMMAND" | grep -qE '\brm\s+-rf\s+/'; then
echo "Dangerous command blocked: rm -rf /" >&2
exit 2 # Exit 2 = block and show error to Claude
fi
exit 0
```
### Smart Validation with Prompt Hook
```json
{
"hooks": {
"PreToolUse": [
{
"matcher": "Write|Edit",
"hooks": [{
"type": "prompt",
"prompt": "Analyze this file operation for safety. Check: 1) No sensitive paths (/etc, ~/.ssh), 2) No credentials in content, 3) No path traversal (..). Tool input: $TOOL_INPUT. Respond with JSON: {\"decision\": \"allow|deny\", \"reason\": \"...\"}",
"timeout": 30
}]
}
]
}
}
```
## Configuration Locations
| Location | Scope | Committed |
|----------|-------|-----------|
| `.claude/settings.json` | Project (team-shared) | Yes |
| `.claude/settings.local.json` | Project (local only) | No |
| `~/.claude/settings.json` | Personal (all projects) | No |
| `plugin/hooks/hooks.json` | Plugin | Yes |
### Plugin Format (hooks.json)
Uses wrapper structure:
```json
{
"description": "Plugin hooks for auto-formatting",
"hooks": {
"PostToolUse": [...]
}
}
```
### Settings Format (settings.json)
Direct structure (no wrapper):
```json
{
"hooks": {
"PostToolUse": [...]
}
}
```
## Matchers
Matchers determine which tool invocations trigger the hook. Case-sensitive.
```json
{"matcher": "Write"} // Exact match
{"matcher": "Edit|Write"} // Multiple tools (OR)
{"matcher": "*"} // All tools
{"matcher": "Write(*.py)"} // File pattern
{"matcher": "Write|Edit(*.ts|*.tsx)"} // Multiple + pattern
{"matcher": "mcp__memory__.*"} // MCP server tools
{"matcher": "mcp__github__create_issue"} // Specific MCP tool
```
**Lifecycle hooks** (SessionStart, SessionEnd, Stop, Notification) use special matchers:
```json
// SessionStart matchers
{"matcher": "startup"} // Initial start
{"matcher": "resume"} // --resume or --continue
{"matcher": "clear"} // After /clear
{"matcher": "compact"} // After compaction
// PreCompact matchers
{"matcher": "manual"} // User triggered /compact
{"matcher": "auto"} // Automatic compaction
```
See [references/matchers.md](references/matchers.md) for advanced patterns.
## Input Format
All hooks receive JSON on stdin:
```json
{
"session_id": "abc123",
"transcript_path": "/path/to/transcript.jsonl",
"cwd": "/current/working/directory",
"hook_event_name": "PreToolUse",
"permission_mode": "ask",
"tool_name": "Write",
"tool_input": {
"file_path": "/project/src/file.ts",
"content": "export const foo = 'bar';"
}
}
```
**Event-specific fields**:
- Tool hooks: `tool_name`, `tool_input`, `tool_result` (PostToolUse)
- UserPromptSubmit: `user_prompt`
- Stop/SubagentStop: `reason`
**Prompt hooks** access fields via placeholders:
- `$ARGUMENTS` - Full context passed to the hook (general-purpose)
- `$TOOL_INPUT` - Tool input for tool-related events
- `$TOOL_RESULT` - Tool result (PostToolUse only)
- `$USER_PROMPT` - User prompt (UserPromptSubmit only)
### Reading Input
**Bash**:
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name')
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
```
**Bun/TypeScript**:
```typescript
#!/usr/bin/env bun
const input = await Bun.stdin.json();
const toolName = input.tool_name;
const filePath = input.tool_input?.file_path;
```
## Output Format
### Exit Codes (Simple)
```bash
exit 0 # Success, continue execution
exit 2 # Block operation (PreToolUse only), stderr shown to Claude
exit 1 # Warning, stderr shown to user, continues
```
### JSON Output (Advanced)
```json
{
"continue": true,
"suppressOutput": false,
"systemMessage": "Context for Claude",
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "allow|deny|ask",
"permissionDecisionReason": "Explanation",
"updatedInput": {"modified": "field"}
}
}
```
**PreToolUse** can modify tool input via `updatedInput` and control permissions via `permissionDecision`.
## Environment Variables
| Variable | Availability | Description |
|----------|--------------|-------------|
| `$CLAUDE_PROJECT_DIR` | All hooks | Project root directory |
| `$CLAUDE_PLUGIN_ROOT` | Plugin hooks | Plugin root (use for portable paths) |
| `$file` | PostToolUse (Write/Edit) | Path to affected file |
| `$CLAUDE_ENV_FILE` | SessionStart | Write env vars here to persist |
| `$CLAUDE_CODE_REMOTE` | All hooks | Set if running in remote context |
**Plugin hooks** should always use `${CLAUDE_PLUGIN_ROOT}` for portability:
```json
{
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/validate.sh"
}
```
**SessionStart** can persist environment variables:
```bash
#!/usr/bin/env bash
# Persist variables for the session
echo "export PROJECT_TYPE=nodejs" >> "$CLAUDE_ENV_FILE"
echo "export API_URL=https://api.example.com" >> "$CLAUDE_ENV_FILE"
```
## Component-Scoped Hooks
Skills, agents, and commands can define hooks in frontmatter. These hooks only run when the component is active.
**Supported events**: PreToolUse, PostToolUse, Stop
### Skill with Hooks
```yaml
---
name: my-skill
description: Skill with validation hooks
hooks:
PreToolUse:
- matcher: "Write|Edit"
hooks:
- type: prompt
prompt: "Validate this write operation for the skill context..."
---
```
### Agent with Hooks
```yaml
---
name: security-reviewer
model: sonnet
hooks:
PreToolUse:
- matcher: "Bash"
hooks:
- type: command
command: "${CLAUDE_PLUGIN_ROOT}/scripts/validate-bash.sh"
Stop:
- matcher: "*"
hooks:
- type: prompt
prompt: "Verify the security review is complete..."
---
```
## Execution Model
**Parallel execution**: All matching hooks run in parallel, not sequentially.
```json
{
"PreToolUse": [{
"matcher": "Write",
"hooks": [
{"type": "command", "command": "check1.sh"}, // Runs in parallel
{"type": "command", "command": "check2.sh"}, // Runs in parallel
{"type": "prompt", "prompt": "Validate..."} // Runs in parallel
]
}]
}
```
**Implications**:
- Hooks cannot see each other's output
- Non-deterministic ordering
- Design for independence
**Hot-swap limitations**: Hook changes require restarting Claude Code. Editing `hooks.json` or hook scripts does not affect the current session.
## Security Best Practices
1. **Validate all input** - Check for path traversal, sensitive paths, injection
2. **Quote shell variables** - Always use `"$VAR"` not `$VAR`
3. **Set timeouts** - Prevent hanging hooks (default: 60s command, 30s prompt)
4. **Use absolute paths** - Via `$CLAUDE_PROJECT_DIR` or `${CLAUDE_PLUGIN_ROOT}`
5. **Handle errors gracefully** - Use `set -euo pipefail` in bash
6. **Don't log sensitive data** - Filter credentials, tokens, API keys
See [references/security.md](references/security.md) for detailed security patterns.
## Debugging
```bash
# Run Claude with debug output
claude --debug
# Test hook manually
echo '{"tool_name": "Write", "tool_input": {"file_path": "test.ts"}}' | ./.claude/hooks/my-hook.sh
# Check transcript for hook execution
# Press Ctrl+R in Claude Code to view transcript
```
**Common issues**:
- Hook not firing: Check matcher syntax, restart Claude Code
- Permission errors: `chmod +x script.sh`
- Timeout: Increase timeout value or optimize script
## Workflow Patterns
### Pre-Commit Quality Gate
```json
{
"hooks": {
"PreToolUse": [
{
"matcher": "Write|Edit",
"hooks": [
{"type": "command", "command": "./.claude/hooks/validate-paths.sh"},
{"type": "command", "command": "./.claude/hooks/check-sensitive.sh"}
]
}
],
"PostToolUse": [
{
"matcher": "Write|Edit(*.ts)",
"hooks": [
{"type": "command", "command": "biome check --write \"$file\""},
{"type": "command", "command": "tsc --noEmit \"$file\""}
]
}
]
}
}
```
### Context Injection
```json
{
"hooks": {
"SessionStart": [{
"matcher": "startup",
"hooks": [{
"type": "command",
"command": "echo \"Branch: $(git branch --show-current)\" && git status --short"
}]
}],
"UserPromptSubmit": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "echo \"Time: $(date '+%Y-%m-%d %H:%M %Z')\""
}]
}]
}
}
```
## References
- [references/hook-types.md](references/hook-types.md) - Detailed documentation for each hook event
- [references/matchers.md](references/matchers.md) - Advanced matcher patterns and MCP tools
- [references/security.md](references/security.md) - Security best practices and validation patterns
- [references/schema.md](references/schema.md) - Complete configuration schema reference
- [references/examples.md](references/examples.md) - Real-world hook implementations
## External Resources
- [Official Hooks Reference](https://code.claude.com/docs/en/hooks)
- [Hooks Guide](https://code.claude.com/docs/en/hooks-guide)
- [Community Examples (disler)](https://github.com/disler/claude-code-hooks-mastery)
- [Claude Code Showcase](https://github.com/ChrisWiles/claude-code-showcase)
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,667 @@
# Hook Types Reference
Detailed documentation for each Claude Code hook event.
## Tool Hooks
### PreToolUse
Executes **before** a tool runs. Can block or modify tool execution.
**Timing**: After Claude creates tool parameters, before tool executes
**Can block**: Yes (exit code 2 or `permissionDecision: "deny"`)
**Supports**: Both `command` and `prompt` hook types
**Input fields**:
- `tool_name`: Name of the tool being called
- `tool_input`: Parameters being passed to the tool
**Output capabilities**:
- Block execution with exit code 2 or `permissionDecision: "deny"`
- Modify input with `updatedInput` in JSON response
- Ask user with `permissionDecision: "ask"`
- Provide context via `systemMessage`
**Common matchers**:
```json
"Bash" // Shell commands
"Write" // File writing
"Edit" // File editing
"Read" // File reading
"Write|Edit" // Multiple tools
"Write(*.py)" // File patterns
"mcp__memory__.*" // MCP tools
"*" // All tools
```
**Use cases**:
- Validate bash commands before execution
- Check file paths for security issues
- Block dangerous operations
- Add context before execution
- Enforce security policies
- Log tool invocations
- Modify tool input on the fly
**Example - Block dangerous commands**:
```json
{
"PreToolUse": [{
"matcher": "Bash",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/validate-bash.sh",
"timeout": 5
}]
}]
}
```
**Example - Smart validation with prompt**:
```json
{
"PreToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "prompt",
"prompt": "Analyze this file operation. Check for: 1) sensitive paths, 2) credentials in content, 3) path traversal. Tool: $TOOL_INPUT. Return {\"decision\": \"allow|deny\", \"reason\": \"...\"}",
"timeout": 30
}]
}]
}
```
**Example - Modify tool input**:
```bash
#!/usr/bin/env bash
# Add timestamp to all file writes
INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path')
CONTENT=$(echo "$INPUT" | jq -r '.tool_input.content')
# Add header to content
NEW_CONTENT="// Modified $(date -Iseconds)\n$CONTENT"
cat << EOF
{
"continue": true,
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "allow",
"updatedInput": {
"file_path": "$FILE_PATH",
"content": "$NEW_CONTENT"
}
}
}
EOF
```
### PostToolUse
Executes **after** a tool completes successfully.
**Timing**: Immediately after tool returns success
**Can block**: No
**Supports**: `command` hook type only
**Input fields**:
- `tool_name`: Name of the tool that ran
- `tool_input`: Parameters that were passed
- `tool_result`: Result returned by the tool
**Special variables**:
- `$file`: Path to affected file (Write/Edit tools only)
**Common matchers**:
```json
"Write|Edit(*.ts)" // TypeScript files
"Write(*.py)" // Python files
"Write|Edit" // Any file modification
"*" // All successful tools
```
**Use cases**:
- Auto-format code files
- Run linters
- Update documentation
- Trigger builds
- Send notifications
- Update indexes
**Example - Auto-format TypeScript**:
```json
{
"PostToolUse": [{
"matcher": "Write|Edit(*.ts|*.tsx)",
"hooks": [{
"type": "command",
"command": "biome check --write \"$file\"",
"timeout": 10
}]
}]
}
```
**Example - Chain multiple formatters**:
```json
{
"PostToolUse": [{
"matcher": "Write|Edit(*.py)",
"hooks": [
{"type": "command", "command": "black \"$file\"", "timeout": 10},
{"type": "command", "command": "isort \"$file\"", "timeout": 5},
{"type": "command", "command": "mypy \"$file\"", "timeout": 15}
]
}]
}
```
### PostToolUseFailure
Executes **after** a tool fails.
**Timing**: After tool execution fails
**Can block**: No
**Supports**: `command` hook type
**Input fields**:
- `tool_name`: Name of the tool that failed
- `tool_input`: Parameters that were passed
- `error`: Error information
**Use cases**:
- Error logging and analytics
- Retry logic
- Failure notifications
- Error recovery
- Debug information collection
**Example - Log failures**:
```json
{
"PostToolUseFailure": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/log-failure.sh",
"timeout": 5
}]
}]
}
```
### PermissionRequest
Executes when a permission dialog would be shown to the user.
**Timing**: Before showing permission dialog
**Can block**: Yes (via `permissionDecision`)
**Supports**: Both `command` and `prompt` hook types
**Input fields**:
- `tool_name`: Tool requesting permission
- `tool_input`: Parameters being requested
**Output capabilities**:
- Auto-allow with `permissionDecision: "allow"`
- Auto-deny with `permissionDecision: "deny"`
- Show dialog with `permissionDecision: "ask"` (default)
**Use cases**:
- Auto-approve known-safe operations
- Auto-deny high-risk operations
- Implement custom permission policies
- Reduce permission fatigue for trusted patterns
**Example - Auto-approve safe reads**:
```json
{
"PermissionRequest": [{
"matcher": "Read",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/auto-approve-reads.sh",
"timeout": 3
}]
}]
}
```
## User Interaction Hooks
### UserPromptSubmit
Executes when user submits a prompt to Claude.
**Timing**: After user submits, before Claude processes
**Can block**: No
**Supports**: Both `command` and `prompt` hook types
**Input fields**:
- `user_prompt`: The prompt text submitted
**Matcher**: Always `*`
**Use cases**:
- Add timestamp or date context
- Add environment information
- Log user activity
- Pre-process or augment prompts
- Add project context
- Skill matching and suggestion
**Example - Add timestamp**:
```json
{
"UserPromptSubmit": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "echo \"Current time: $(date '+%Y-%m-%d %H:%M:%S %Z')\"",
"timeout": 2
}]
}]
}
```
**Example - Add git context**:
```json
{
"UserPromptSubmit": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "echo \"Branch: $(git branch --show-current 2>/dev/null || echo 'N/A')\"",
"timeout": 3
}]
}]
}
```
### Notification
Executes when Claude Code sends a notification.
**Timing**: When notification is triggered
**Can block**: No
**Supports**: `command` hook type
**Input fields**:
- Notification message and metadata
**Matcher**: Always `*`
**Use cases**:
- Send to external systems (Slack, email)
- Log notifications
- Trigger alerts
- Update dashboards
- Archive important messages
- Text-to-speech announcements
**Example - Slack integration**:
```json
{
"Notification": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/send-to-slack.sh",
"timeout": 10
}]
}]
}
```
## Agent Lifecycle Hooks
### Stop
Executes when main Claude agent finishes responding.
**Timing**: After Claude completes response
**Can block**: No
**Supports**: Both `command` and `prompt` hook types
**Input fields**:
- `reason`: Why the agent stopped
**Matcher**: Always `*`
**Use cases**:
- Clean up temporary resources
- Send completion notifications
- Update external systems
- Log session metrics
- Archive conversation
- Verify task completion
**Example - Completion notification**:
```json
{
"Stop": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "echo 'Task completed at $(date +%H:%M)'",
"timeout": 2
}]
}]
}
```
**Example - Verify completeness with prompt**:
```json
{
"Stop": [{
"matcher": "*",
"hooks": [{
"type": "prompt",
"prompt": "Review if the task was completed satisfactorily. Check for any unfinished work or follow-up items.",
"timeout": 30
}]
}]
}
```
### SubagentStart
Executes when a subagent (Task tool) spawns.
**Timing**: When subagent is created
**Can block**: No
**Supports**: `command` hook type
**Input fields**:
- Subagent metadata
**Matcher**: Always `*`
**Use cases**:
- Track subagent spawning
- Log subagent parameters
- Monitor parallel execution
- Resource allocation
**Example - Track subagent usage**:
```json
{
"SubagentStart": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/log-subagent-start.sh",
"timeout": 2
}]
}]
}
```
### SubagentStop
Executes when a subagent (Task tool) finishes.
**Timing**: After subagent completes
**Can block**: No
**Supports**: Both `command` and `prompt` hook types
**Input fields**:
- `reason`: Why the subagent stopped
- Subagent result metadata
**Matcher**: Always `*`
**Use cases**:
- Track subagent completion
- Log subagent results
- Trigger follow-up actions
- Update metrics
- Debug subagent behavior
**Example - Log subagent completion**:
```json
{
"SubagentStop": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/log-subagent-stop.sh",
"timeout": 3
}]
}]
}
```
## Session Lifecycle Hooks
### SessionStart
Executes when session starts or resumes.
**Timing**: At session initialization
**Can block**: No
**Supports**: `command` hook type
**Input fields**:
- `reason`: Start type
**Matchers**:
```json
"startup" // Claude Code starts fresh
"resume" // Session resumes (--resume or --continue)
"clear" // After /clear command
"compact" // After compaction
```
**Special capability**: Persist environment variables via `$CLAUDE_ENV_FILE`
**Use cases**:
- Display welcome message
- Show git status
- Load project context
- Check for updates
- Initialize resources
- Set session-wide variables
**Example - Welcome with git status**:
```json
{
"SessionStart": [{
"matcher": "startup",
"hooks": [{
"type": "command",
"command": "echo 'Welcome!' && git status --short",
"timeout": 5
}]
}]
}
```
**Example - Persist environment variables**:
```bash
#!/usr/bin/env bash
# This script runs on SessionStart
# Persist variables for the entire session
# Detect project type and persist
if [[ -f "package.json" ]]; then
echo "export PROJECT_TYPE=nodejs" >> "$CLAUDE_ENV_FILE"
elif [[ -f "Cargo.toml" ]]; then
echo "export PROJECT_TYPE=rust" >> "$CLAUDE_ENV_FILE"
fi
# Set API endpoints
echo "export API_URL=https://api.example.com" >> "$CLAUDE_ENV_FILE"
```
### SessionEnd
Executes when session ends.
**Timing**: Before session terminates
**Can block**: No
**Supports**: `command` hook type
**Input fields**:
- `reason`: End type
**Matchers** (reasons):
```json
"clear" // User ran /clear
"logout" // User logged out
"prompt_input_exit" // Exited during prompt input
"other" // Other reasons
```
**Use cases**:
- Clean up resources
- Save state
- Log session metrics
- Send completion notifications
- Archive transcripts
**Example - Cleanup**:
```json
{
"SessionEnd": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/cleanup.sh",
"timeout": 5
}]
}]
}
```
### PreCompact
Executes before conversation compacts.
**Timing**: Before compact operation starts
**Can block**: No
**Supports**: `command` hook type
**Input fields**:
- Compact trigger type
**Matchers**:
```json
"manual" // User triggered via /compact
"auto" // Automatic compact (context limit)
```
**Use cases**:
- Backup conversation
- Archive important context
- Update external summaries
- Log compact events
- Prepare for context reset
**Example - Backup before compact**:
```json
{
"PreCompact": [{
"matcher": "manual|auto",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/backup-conversation.sh",
"timeout": 10
}]
}]
}
```
## Hook Type Comparison
| Event | Can Block | Prompt Type | Command Type | Common Use |
|-------|-----------|-------------|--------------|------------|
| PreToolUse | Yes | Yes | Yes | Validation, security |
| PostToolUse | No | No | Yes | Formatting, linting |
| PostToolUseFailure | No | No | Yes | Error logging |
| PermissionRequest | Yes | Yes | Yes | Auto-approve/deny |
| UserPromptSubmit | No | Yes | Yes | Context injection |
| Notification | No | No | Yes | External alerts |
| Stop | No | Yes | Yes | Cleanup, verification |
| SubagentStart | No | No | Yes | Tracking |
| SubagentStop | No | Yes | Yes | Logging |
| SessionStart | No | No | Yes | Initialization |
| SessionEnd | No | No | Yes | Cleanup |
| PreCompact | No | No | Yes | Backup |
## Tool Use ID Correlation
PreToolUse and PostToolUse events for the same tool invocation share a tool use ID, allowing you to correlate them:
```bash
#!/usr/bin/env bash
# PreToolUse - save state
INPUT=$(cat)
TOOL_USE_ID=$(echo "$INPUT" | jq -r '.tool_use_id')
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name')
# Save start time for correlation
echo "$(date +%s%N)" > "/tmp/claude-tool-$TOOL_USE_ID.start"
```
```bash
#!/usr/bin/env bash
# PostToolUse - calculate duration
INPUT=$(cat)
TOOL_USE_ID=$(echo "$INPUT" | jq -r '.tool_use_id')
START=$(cat "/tmp/claude-tool-$TOOL_USE_ID.start" 2>/dev/null || echo "0")
END=$(date +%s%N)
DURATION_MS=$(( (END - START) / 1000000 ))
echo "Tool completed in ${DURATION_MS}ms"
rm -f "/tmp/claude-tool-$TOOL_USE_ID.start"
```
@@ -0,0 +1,302 @@
# Matcher Patterns Reference
Matchers determine which tool invocations or events trigger a hook. They are case-sensitive strings that support exact matching, regex patterns, wildcards, and file patterns.
## Matcher Types
### Simple String Match
Match exact tool name:
```json
{"matcher": "Write"} // Only Write tool
{"matcher": "Edit"} // Only Edit tool
{"matcher": "Bash"} // Only Bash tool
{"matcher": "Read"} // Only Read tool
{"matcher": "Grep"} // Only Grep tool
{"matcher": "Glob"} // Only Glob tool
{"matcher": "Task"} // Only Task tool (subagents)
{"matcher": "WebFetch"} // Only WebFetch tool
{"matcher": "WebSearch"}// Only WebSearch tool
```
### OR Patterns (Pipe)
Match multiple tools with `|`:
```json
{"matcher": "Edit|Write"} // Edit OR Write
{"matcher": "Read|Grep|Glob"} // Any read/search operation
{"matcher": "Write|Edit|NotebookEdit"} // Multiple specific tools
{"matcher": "WebFetch|WebSearch"} // Web operations
```
### Wildcard Match
Match all tools with `*`:
```json
{"matcher": "*"} // Matches everything
```
**Use cases**:
- Logging all tool usage
- Global validation
- Universal context injection
- Metrics collection
### File Pattern Match
Match tools operating on specific file types with `(pattern)`:
```json
{"matcher": "Write(*.py)"} // Write Python files
{"matcher": "Edit(*.ts)"} // Edit TypeScript files
{"matcher": "Write(*.md)"} // Write Markdown files
{"matcher": "Write|Edit(*.js)"} // Write or Edit JavaScript
{"matcher": "Write|Edit(*.ts|*.tsx)"} // TypeScript and TSX files
```
**Supported patterns**:
- `*.ext` - Any file with extension
- `path/*.ext` - Files in specific directory (relative to project)
- `**/*.ext` - Recursive file match
**More examples**:
```json
{"matcher": "Write(*.tsx)"} // React components
{"matcher": "Write|Edit(*.rs)"} // Rust files
{"matcher": "Write(src/**/*.ts)"} // TS files in src/
{"matcher": "Edit(.env*)"} // .env files
{"matcher": "Write(*.json)"} // JSON files
{"matcher": "Write|Edit(*.yaml|*.yml)"} // YAML files
```
### Regex Patterns
Full regex support for complex matching:
```json
{"matcher": "^Write$"} // Exactly "Write", no prefix/suffix
{"matcher": ".*Edit.*"} // Contains "Edit" anywhere
{"matcher": "Notebook.*"} // Starts with "Notebook"
{"matcher": "Bash|WebFetch"} // Bash or WebFetch
```
**Regex features**:
- `|` - OR operator
- `.` - Any character
- `*` - Zero or more
- `+` - One or more
- `^` - Start of string
- `$` - End of string
- `[abc]` - Character class
- `\w` - Word character
- `\d` - Digit
## MCP Tool Matchers
MCP (Model Context Protocol) tools follow naming: `mcp__<server-name>__<tool-name>`
### Match All MCP Tools
```json
{"matcher": "mcp__.*__.*"} // Any MCP tool from any server
```
### Match Specific Server
```json
{"matcher": "mcp__memory__.*"} // All memory MCP tools
{"matcher": "mcp__github__.*"} // All GitHub MCP tools
{"matcher": "mcp__filesystem__.*"} // All filesystem MCP tools
{"matcher": "mcp__brave-search__.*"}// All Brave search tools
```
### Match Specific Tools
```json
{"matcher": "mcp__github__create_issue"} // Specific GitHub tool
{"matcher": "mcp__github__create_pull_request"} // Create PR tool
{"matcher": "mcp__memory__add_memory"} // Add to memory
{"matcher": "mcp__memory__search_memory"} // Search memory
```
### Complex MCP Patterns
```json
// All delete operations across MCP servers
{"matcher": "mcp__.*__delete.*"}
// Create operations in GitHub
{"matcher": "mcp__github__(create_issue|create_comment|create_pull_request)"}
// All read operations in filesystem
{"matcher": "mcp__filesystem__(read|list|search).*"}
// Dangerous operations to block
{"matcher": "mcp__.*(delete|remove|destroy).*"}
```
## Lifecycle Event Matchers
Some hooks use special matchers for lifecycle events instead of tool names.
### SessionStart Matchers
```json
{"matcher": "startup"} // Fresh Claude Code start
{"matcher": "resume"} // Session resume (--resume, --continue)
{"matcher": "clear"} // After /clear command
{"matcher": "compact"} // After context compaction
{"matcher": "*"} // Any session start type
```
### SessionEnd Matchers
```json
{"matcher": "clear"} // User ran /clear
{"matcher": "logout"} // User logged out
{"matcher": "prompt_input_exit"} // Exited during prompt
{"matcher": "other"} // Other reasons
{"matcher": "*"} // Any end reason
```
### PreCompact Matchers
```json
{"matcher": "manual"} // User triggered /compact
{"matcher": "auto"} // Automatic compaction
{"matcher": "*"} // Any compact type
```
### Stop/SubagentStop Matchers
```json
{"matcher": "*"} // Always matches (lifecycle events)
```
## Complex Matcher Examples
### Multiple Tools with File Patterns
```json
// Format Python or TypeScript
{"matcher": "Write|Edit(*.py)|Write|Edit(*.ts)"}
// All code files
{"matcher": "Write|Edit(*.ts|*.tsx|*.js|*.jsx|*.py|*.rs)"}
```
### Excluding Patterns
There's no direct exclusion, but you can handle this in the hook script:
```bash
#!/usr/bin/env bash
INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
# Skip test files
if [[ "$FILE_PATH" =~ \.(test|spec)\. ]]; then
exit 0
fi
# Skip node_modules
if [[ "$FILE_PATH" =~ node_modules/ ]]; then
exit 0
fi
# Continue with validation...
```
### Combining with Regex
```json
// Bash or any MCP tool
{"matcher": "Bash|mcp__.*__.*"}
// Read operations (multiple tools)
{"matcher": "Read|Grep|Glob|WebFetch"}
// File modifications only
{"matcher": "Write|Edit|NotebookEdit"}
```
## Matcher Debugging
If your hook isn't firing, check:
1. **Case sensitivity**: `Write` works, `write` doesn't
2. **Exact tool names**: Use `claude --debug` to see actual tool names
3. **File patterns**: Ensure the pattern matches the file path format
4. **MCP naming**: Verify server and tool names match exactly
### Testing Matchers
```bash
# See what tools Claude is calling
claude --debug 2>&1 | grep "tool_name"
# Test regex patterns
echo "Write" | grep -E '^Write$' # Should match
echo "WriteFile" | grep -E '^Write$' # Should not match
```
## Common Matcher Patterns
### Security Validation
```json
// All file operations
{"matcher": "Write|Edit|Read"}
// Dangerous commands
{"matcher": "Bash"}
// Network operations
{"matcher": "WebFetch|WebSearch|mcp__.*"}
```
### Auto-Formatting
```json
// TypeScript/JavaScript
{"matcher": "Write|Edit(*.ts|*.tsx|*.js|*.jsx)"}
// Python
{"matcher": "Write|Edit(*.py)"}
// Rust
{"matcher": "Write|Edit(*.rs)"}
// All supported
{"matcher": "Write|Edit(*.ts|*.tsx|*.py|*.rs|*.go)"}
```
### Logging
```json
// All tool operations
{"matcher": "*"}
// All MCP operations
{"matcher": "mcp__.*__.*"}
// File operations only
{"matcher": "Write|Edit|Read|Grep|Glob"}
```
### External Integration
```json
// GitHub operations
{"matcher": "mcp__github__.*"}
// Memory operations
{"matcher": "mcp__memory__.*"}
// All external services
{"matcher": "mcp__.*__.*|WebFetch|WebSearch"}
```
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,533 @@
# Security Best Practices
Comprehensive security guidance for Claude Code hooks.
## Input Validation
### Validate All Input
Always validate and sanitize hook input before use:
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
# Validate input exists
if [[ -z "$FILE_PATH" ]]; then
echo "Error: file_path missing" >&2
exit 1
fi
# Validate format
if [[ ! "$FILE_PATH" =~ ^[a-zA-Z0-9_./-]+$ ]]; then
echo "Error: invalid characters in file path" >&2
exit 2
fi
```
### Check for Path Traversal
Block directory traversal attacks:
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
# Block path traversal
if echo "$FILE_PATH" | grep -qE '\.\./'; then
cat << EOF >&2
Path traversal detected: $FILE_PATH
Paths containing '..' are not allowed.
EOF
exit 2
fi
# Block absolute paths outside project
if [[ "$FILE_PATH" == /* ]] && [[ ! "$FILE_PATH" == "$CLAUDE_PROJECT_DIR"* ]]; then
echo "Access outside project directory blocked: $FILE_PATH" >&2
exit 2
fi
```
### Block Sensitive System Paths
Prevent access to system files:
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
# Blocked system paths
BLOCKED_PATHS=(
'^/etc/'
'^/root/'
'^/home/[^/]+/\.ssh/'
'^/var/log/'
'^/sys/'
'^/proc/'
'^/boot/'
'^/usr/bin/'
'^/usr/sbin/'
)
for pattern in "${BLOCKED_PATHS[@]}"; do
if echo "$FILE_PATH" | grep -qE "$pattern"; then
cat << EOF >&2
Access to sensitive system path blocked: $FILE_PATH
This path is restricted for security reasons.
EOF
exit 2
fi
done
```
### Detect Sensitive Files
Warn or block access to sensitive project files:
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
# Sensitive file patterns
SENSITIVE_PATTERNS=(
'\.env$'
'\.env\.'
'id_rsa'
'id_ed25519'
'\.pem$'
'\.key$'
'\.p12$'
'credentials'
'password'
'token'
'secret'
'\.git/config$'
'\.npmrc$'
'\.pypirc$'
)
for pattern in "${SENSITIVE_PATTERNS[@]}"; do
if echo "$FILE_PATH" | grep -qiE "$pattern"; then
cat << EOF >&2
Warning: Accessing sensitive file: $FILE_PATH
This file may contain sensitive information.
EOF
# Could exit 2 to block, or continue with warning
fi
done
```
## Command Injection Prevention
### Always Quote Variables
```bash
# WRONG - vulnerable to injection
rm $FILE_PATH
cd $DIRECTORY
echo $CONTENT
# CORRECT - properly quoted
rm "$FILE_PATH"
cd "$DIRECTORY"
echo "$CONTENT"
```
### Avoid eval
```bash
# WRONG - dangerous
eval "$USER_COMMAND"
# CORRECT - use specific commands
if [[ "$USER_COMMAND" == "format" ]]; then
black "$FILE_PATH"
fi
```
### Validate Command Patterns
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command // empty')
# Block dangerous command patterns
DANGEROUS_PATTERNS=(
'\brm\s+-rf\s+/' # rm -rf /
'\brm\s+--no-preserve-root' # rm --no-preserve-root
'\bmkfs\b' # filesystem format
'\bdd\s+if=' # disk destruction
'\bformat\s+[cC]:' # Windows format
'>\s*/dev/sd[a-z]' # overwrite disk
':()\{\s*:\|\:&\s*\};:' # Fork bomb
'\bchmod\s+777\s+/' # Dangerous permissions
'\bchown\s+.*\s+/' # System ownership change
'\bcurl\s+.*\|\s*bash' # Pipe to bash
'\bwget\s+.*\|\s*bash' # Pipe to bash
'\bsudo\s+rm' # Sudo rm
'\bgit\s+push\s+--force\s+origin\s+main' # Force push main
)
for pattern in "${DANGEROUS_PATTERNS[@]}"; do
if echo "$COMMAND" | grep -qE "$pattern"; then
cat << EOF >&2
Dangerous command blocked: $COMMAND
Pattern matched: $pattern
EOF
exit 2
fi
done
```
## Path Security
### Use Absolute Paths
Always construct paths from known roots:
```bash
#!/usr/bin/env bash
# Use CLAUDE_PROJECT_DIR for project paths
SCRIPT_PATH="$CLAUDE_PROJECT_DIR/.claude/hooks/helper.sh"
# Use CLAUDE_PLUGIN_ROOT for plugin paths
PLUGIN_SCRIPT="${CLAUDE_PLUGIN_ROOT}/scripts/validate.sh"
# Never rely on relative paths
# BAD: ./scripts/validate.sh
# GOOD: "$CLAUDE_PROJECT_DIR/.claude/scripts/validate.sh"
```
### Validate Script Existence
```bash
#!/usr/bin/env bash
SCRIPT_PATH="$CLAUDE_PROJECT_DIR/.claude/hooks/helper.sh"
# Check exists
if [[ ! -f "$SCRIPT_PATH" ]]; then
echo "Error: script not found: $SCRIPT_PATH" >&2
exit 1
fi
# Check executable
if [[ ! -x "$SCRIPT_PATH" ]]; then
echo "Error: script not executable: $SCRIPT_PATH" >&2
exit 1
fi
# Execute safely
"$SCRIPT_PATH" "$@"
```
### Resolve Symlinks
```bash
#!/usr/bin/env bash
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path')
# Resolve symlinks to check actual destination
REAL_PATH=$(realpath "$FILE_PATH" 2>/dev/null || echo "$FILE_PATH")
# Check the real path is within project
if [[ ! "$REAL_PATH" == "$CLAUDE_PROJECT_DIR"* ]]; then
echo "Symlink points outside project: $FILE_PATH -> $REAL_PATH" >&2
exit 2
fi
```
## Sensitive Data Protection
### Never Log Sensitive Data
```bash
#!/usr/bin/env bash
INPUT=$(cat)
# WRONG - logs everything including secrets
echo "Input: $INPUT" >> /tmp/debug.log
# CORRECT - log only safe fields
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name')
echo "Tool: $TOOL_NAME" >> /tmp/debug.log
# CORRECT - filter sensitive fields before logging
echo "$INPUT" | jq 'del(.tool_input.password, .tool_input.api_key, .tool_input.token)' >> /tmp/debug.log
```
### Sanitize Output
```bash
#!/usr/bin/env bash
INPUT=$(cat)
CONTENT=$(echo "$INPUT" | jq -r '.tool_input.content // empty')
# Check for secrets in content
if echo "$CONTENT" | grep -qiE '(password|api_key|secret|token)\s*[=:]\s*\S+'; then
echo "Warning: Potential secret detected in content" >&2
# Could block or just warn
fi
```
### Protect Environment Variables
```bash
#!/usr/bin/env bash
# Don't expose sensitive env vars
# WRONG
echo "API_KEY=$API_KEY"
env | grep -i secret
# CORRECT - never print secrets
echo "API key configured: $([ -n "$API_KEY" ] && echo "yes" || echo "no")"
```
## Timeout Protection
### Set Appropriate Timeouts
```json
{
"hooks": {
"PreToolUse": [{
"matcher": "Bash",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/validate.sh",
"timeout": 5
}]
}],
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "./.claude/hooks/format.sh",
"timeout": 30
}]
}]
}
}
```
**Guidelines**:
- Quick validation: 3-5 seconds
- Formatting: 10-30 seconds
- Network operations: 30-60 seconds
- Default: 60 seconds for command, 30 seconds for prompt
### Handle Timeouts Gracefully
```bash
#!/usr/bin/env bash
set -euo pipefail
# Set internal timeout for network operations
timeout 10 curl -s https://api.example.com/validate || {
echo "API validation skipped (timeout)" >&2
exit 0 # Don't block on timeout
}
```
## Error Handling
### Use Strict Mode
```bash
#!/usr/bin/env bash
set -euo pipefail # Exit on error, undefined vars, pipe failures
# Also consider:
set -E # Inherit ERR trap in functions
trap 'echo "Error on line $LINENO" >&2' ERR
```
### Validate Dependencies
```bash
#!/usr/bin/env bash
set -euo pipefail
# Check required tools exist
for cmd in jq git curl; do
if ! command -v "$cmd" &>/dev/null; then
echo "Error: $cmd not installed" >&2
exit 1
fi
done
```
### Handle JSON Parsing Errors
```bash
#!/usr/bin/env bash
set -euo pipefail
# Read input with error handling
INPUT=$(cat) || {
echo "Error: failed to read stdin" >&2
exit 1
}
# Parse with validation
if ! echo "$INPUT" | jq empty 2>/dev/null; then
echo "Error: invalid JSON input" >&2
exit 1
fi
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name // empty')
if [[ -z "$TOOL_NAME" ]]; then
echo "Error: tool_name missing" >&2
exit 1
fi
```
## Permission Control
### PreToolUse Permission Decisions
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name')
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
# Auto-approve reads of non-sensitive files
if [[ "$TOOL_NAME" == "Read" ]] && [[ ! "$FILE_PATH" =~ \.(env|key|pem)$ ]]; then
cat << EOF
{
"continue": true,
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "allow"
}
}
EOF
exit 0
fi
# Ask for writes to core files
if [[ "$FILE_PATH" =~ src/core/ ]]; then
cat << EOF
{
"continue": true,
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "ask",
"permissionDecisionReason": "Write to core module requires confirmation"
}
}
EOF
exit 0
fi
# Default: allow
exit 0
```
### PermissionRequest Hook
```bash
#!/usr/bin/env bash
set -euo pipefail
INPUT=$(cat)
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name')
# Auto-deny certain operations
if [[ "$TOOL_NAME" =~ (delete|destroy|remove) ]]; then
cat << EOF
{
"hookSpecificOutput": {
"permissionDecision": "deny",
"permissionDecisionReason": "Destructive operations require manual approval"
}
}
EOF
exit 0
fi
```
## Audit Trail
### Log All Operations
```bash
#!/usr/bin/env bash
set -euo pipefail
AUDIT_FILE="$CLAUDE_PROJECT_DIR/.claude/audit.log"
INPUT=$(cat)
TIMESTAMP=$(date -Iseconds)
HOOK_EVENT=$(echo "$INPUT" | jq -r '.hook_event_name')
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name // "N/A"')
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // "N/A"')
SESSION_ID=$(echo "$INPUT" | jq -r '.session_id')
# Create audit entry (filter sensitive data)
AUDIT_ENTRY=$(jq -n \
--arg ts "$TIMESTAMP" \
--arg event "$HOOK_EVENT" \
--arg tool "$TOOL_NAME" \
--arg file "$FILE_PATH" \
--arg session "$SESSION_ID" \
--arg user "$USER" \
'{
timestamp: $ts,
event: $event,
tool: $tool,
file: $file,
session: $session,
user: $user
}')
echo "$AUDIT_ENTRY" >> "$AUDIT_FILE"
# Rotate: keep only last 10000 entries
tail -n 10000 "$AUDIT_FILE" > "$AUDIT_FILE.tmp" && mv "$AUDIT_FILE.tmp" "$AUDIT_FILE"
exit 0
```
## Security Checklist
### Before Deploying Hooks
- [ ] All input validated and sanitized
- [ ] Path traversal attacks blocked
- [ ] Sensitive system paths protected
- [ ] All shell variables quoted
- [ ] No eval or command injection vectors
- [ ] Sensitive data not logged
- [ ] Appropriate timeouts set
- [ ] Dependencies validated
- [ ] Error handling robust
- [ ] Audit trail enabled
### Regular Security Review
- [ ] Review hook scripts for vulnerabilities
- [ ] Check for hardcoded secrets
- [ ] Verify timeout values are appropriate
- [ ] Audit logged data for sensitive info leaks
- [ ] Update blocked patterns for new threats
- [ ] Test hooks with malicious input
@@ -0,0 +1,550 @@
#!/usr/bin/env bash
# scaffold-hook.sh - Generate hook configuration and script from templates
set -euo pipefail
# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
# Help text
show_help() {
cat << EOF
Usage: $(basename "$0") <hook-name> [options]
Generate a new Claude Code hook with configuration and script.
Arguments:
hook-name Name of the hook (kebab-case)
Options:
-e, --event Event type (required): PreToolUse, PostToolUse,
UserPromptSubmit, Notification, Stop, SubagentStop,
PreCompact, SessionStart, SessionEnd
-m, --matcher Matcher pattern (default: *)
-t, --type Template type: validation, formatting, logging,
notification, context (default: validation)
-l, --language Script language: bash, typescript, python (default: bash)
-o, --output Output directory for script (default: .claude/hooks)
-c, --config Config file to update (default: .claude/settings.json)
-p, --personal Use personal config (~/.claude/settings.json)
--timeout Hook timeout in seconds (default: 30)
-i, --interactive Interactive mode (prompts for all values)
-h, --help Show this help
Examples:
# Simple validation hook
$(basename "$0") validate-bash -e PreToolUse -m Bash
# Python formatter with PostToolUse
$(basename "$0") format-python -e PostToolUse -m "Write(*.py)" -t formatting
# Interactive mode
$(basename "$0") my-hook -i
# Personal hook with custom output
$(basename "$0") log-ops -e PreToolUse -m "*" -p
Event Types:
PreToolUse - Before tool execution (can block)
PostToolUse - After tool completes successfully
UserPromptSubmit - When user submits prompt
Notification - When notification sent
Stop - When main agent finishes
SubagentStop - When subagent finishes
PreCompact - Before conversation compacts
SessionStart - When session starts/resumes
SessionEnd - When session ends
Matcher Examples:
"*" - Match all tools
"Write" - Match Write tool only
"Write|Edit" - Match Write or Edit
"Write(*.py)" - Match Python file writes
"mcp__memory__.*" - Match memory MCP tools
EOF
}
# Parse arguments
HOOK_NAME=""
EVENT_TYPE=""
MATCHER="*"
TEMPLATE_TYPE="validation"
LANGUAGE="bash"
OUTPUT_DIR=".claude/hooks"
CONFIG_FILE=".claude/settings.json"
TIMEOUT=30
INTERACTIVE=false
while [[ $# -gt 0 ]]; do
case $1 in
-h|--help)
show_help
exit 0
;;
-e|--event)
EVENT_TYPE="$2"
shift 2
;;
-m|--matcher)
MATCHER="$2"
shift 2
;;
-t|--type)
TEMPLATE_TYPE="$2"
shift 2
;;
-l|--language)
LANGUAGE="$2"
shift 2
;;
-o|--output)
OUTPUT_DIR="$2"
shift 2
;;
-c|--config)
CONFIG_FILE="$2"
shift 2
;;
-p|--personal)
CONFIG_FILE="$HOME/.claude/settings.json"
OUTPUT_DIR="$HOME/.claude/hooks"
shift
;;
--timeout)
TIMEOUT="$2"
shift 2
;;
-i|--interactive)
INTERACTIVE=true
shift
;;
-*)
echo -e "${RED}Error: Unknown option $1${NC}"
show_help
exit 1
;;
*)
HOOK_NAME="$1"
shift
;;
esac
done
# Validate hook name
if [[ -z "$HOOK_NAME" ]]; then
echo -e "${RED}Error: Hook name required${NC}"
show_help
exit 1
fi
# Validate hook name format (kebab-case)
if [[ ! "$HOOK_NAME" =~ ^[a-z0-9]+(-[a-z0-9]+)*$ ]]; then
echo -e "${RED}Error: Hook name must be kebab-case (e.g., my-hook)${NC}"
exit 1
fi
# Interactive mode
if [[ "$INTERACTIVE" == "true" ]]; then
echo -e "${BLUE}=== Interactive Hook Setup ===${NC}"
echo
# Event type
echo -e "${BLUE}Select event type:${NC}"
echo "1) PreToolUse - Before tool execution (can block)"
echo "2) PostToolUse - After tool completes"
echo "3) UserPromptSubmit - When user submits prompt"
echo "4) Notification - When notification sent"
echo "5) Stop - When agent finishes"
echo "6) SubagentStop - When subagent finishes"
echo "7) PreCompact - Before compact"
echo "8) SessionStart - Session starts"
echo "9) SessionEnd - Session ends"
read -r -p "Enter number (1-9): " EVENT_NUM
case $EVENT_NUM in
1) EVENT_TYPE="PreToolUse" ;;
2) EVENT_TYPE="PostToolUse" ;;
3) EVENT_TYPE="UserPromptSubmit" ;;
4) EVENT_TYPE="Notification" ;;
5) EVENT_TYPE="Stop" ;;
6) EVENT_TYPE="SubagentStop" ;;
7) EVENT_TYPE="PreCompact" ;;
8) EVENT_TYPE="SessionStart" ;;
9) EVENT_TYPE="SessionEnd" ;;
*) echo -e "${RED}Invalid selection${NC}"; exit 1 ;;
esac
# Matcher
echo
echo -e "${BLUE}Enter matcher pattern (e.g., 'Write', '*.py', '*'):${NC}"
read -r MATCHER
# Template type
echo
echo -e "${BLUE}Select template type:${NC}"
echo "1) validation - Validate input and block if needed"
echo "2) formatting - Format files after modification"
echo "3) logging - Log operations"
echo "4) notification - Send notifications"
echo "5) context - Add context to prompts"
read -r -p "Enter number (1-5): " TEMPLATE_NUM
case $TEMPLATE_NUM in
1) TEMPLATE_TYPE="validation" ;;
2) TEMPLATE_TYPE="formatting" ;;
3) TEMPLATE_TYPE="logging" ;;
4) TEMPLATE_TYPE="notification" ;;
5) TEMPLATE_TYPE="context" ;;
*) echo -e "${RED}Invalid selection${NC}"; exit 1 ;;
esac
# Language
echo
echo -e "${BLUE}Select script language:${NC}"
echo "1) bash"
echo "2) typescript"
echo "3) python"
read -r -p "Enter number (1-3): " LANG_NUM
case $LANG_NUM in
1) LANGUAGE="bash" ;;
2) LANGUAGE="typescript" ;;
3) LANGUAGE="python" ;;
*) echo -e "${RED}Invalid selection${NC}"; exit 1 ;;
esac
# Timeout
echo
read -r -p "Timeout in seconds (default: 30): " INPUT_TIMEOUT
if [[ -n "$INPUT_TIMEOUT" ]]; then
if [[ "$INPUT_TIMEOUT" =~ ^[0-9]+$ ]] && [[ "$INPUT_TIMEOUT" -gt 0 ]] && [[ "$INPUT_TIMEOUT" -le 300 ]]; then
TIMEOUT="$INPUT_TIMEOUT"
else
echo -e "${YELLOW}Warning: Invalid timeout value, using default (30s)${NC}"
fi
fi
fi
# Validate event type
VALID_EVENTS=(PreToolUse PostToolUse UserPromptSubmit Notification Stop SubagentStop PreCompact SessionStart SessionEnd)
if [[ -z "$EVENT_TYPE" ]]; then
echo -e "${RED}Error: Event type required (-e/--event)${NC}"
echo "Valid events: ${VALID_EVENTS[*]}"
exit 1
fi
valid_event=false
for evt in "${VALID_EVENTS[@]}"; do
if [[ "$evt" == "$EVENT_TYPE" ]]; then
valid_event=true
break
fi
done
if [[ "$valid_event" == "false" ]]; then
echo -e "${RED}Error: Invalid event type: $EVENT_TYPE${NC}"
echo "Valid events: ${VALID_EVENTS[*]}"
exit 1
fi
# Validate language
VALID_LANGUAGES=(bash typescript python)
valid_lang=false
for lang in "${VALID_LANGUAGES[@]}"; do
if [[ "$lang" == "$LANGUAGE" ]]; then
valid_lang=true
break
fi
done
if [[ "$valid_lang" == "false" ]]; then
echo -e "${RED}Error: Invalid language: $LANGUAGE${NC}"
echo "Valid languages: ${VALID_LANGUAGES[*]}"
exit 1
fi
# Determine script extension
case "$LANGUAGE" in
bash) SCRIPT_EXT="sh" ;;
typescript) SCRIPT_EXT="ts" ;;
python) SCRIPT_EXT="py" ;;
esac
# Create output directory
mkdir -p "$OUTPUT_DIR"
SCRIPT_PATH="$OUTPUT_DIR/$HOOK_NAME.$SCRIPT_EXT"
# Check if script already exists
if [[ -f "$SCRIPT_PATH" ]]; then
echo -e "${YELLOW}Warning: Script already exists: $SCRIPT_PATH${NC}"
read -r -p "Overwrite? (y/N): " CONFIRM
if [[ ! "$CONFIRM" =~ ^[Yy]$ ]]; then
echo "Aborted"
exit 0
fi
fi
# Generate script based on template and language
case "$LANGUAGE" in
bash)
cat > "$SCRIPT_PATH" << 'BASH_EOF'
#!/usr/bin/env bash
# HOOK_NAME - DESCRIPTION
set -euo pipefail
# Read input from stdin
INPUT=$(cat)
# Parse JSON input
HOOK_EVENT=$(echo "$INPUT" | jq -r '.hook_event_name')
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name // empty')
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
# TEMPLATE_LOGIC
exit 0
BASH_EOF
;;
typescript)
cat > "$SCRIPT_PATH" << 'TS_EOF'
#!/usr/bin/env bun
// HOOK_NAME - DESCRIPTION
import { stdin } from "process";
interface HookInput {
session_id: string;
transcript_path: string;
cwd: string;
hook_event_name: string;
tool_name?: string;
tool_input?: Record<string, any>;
reason?: string;
}
// Read stdin
const chunks: Buffer[] = [];
for await (const chunk of stdin) {
chunks.push(chunk);
}
const input: HookInput = JSON.parse(Buffer.concat(chunks).toString());
// Parse input
const hookEvent = input.hook_event_name;
const toolName = input.tool_name || "";
const filePath = input.tool_input?.file_path || "";
// TEMPLATE_LOGIC
process.exit(0);
TS_EOF
;;
python)
cat > "$SCRIPT_PATH" << 'PY_EOF'
#!/usr/bin/env python3
"""HOOK_NAME - DESCRIPTION"""
import json
import sys
from typing import Any, Dict
def main() -> None:
"""Main hook logic"""
# Read input from stdin
try:
input_data: Dict[str, Any] = json.load(sys.stdin)
except json.JSONDecodeError as e:
print(f"Error parsing JSON: {e}", file=sys.stderr)
sys.exit(1)
# Parse input
hook_event = input_data.get("hook_event_name", "")
tool_name = input_data.get("tool_name", "")
file_path = input_data.get("tool_input", {}).get("file_path", "")
# TEMPLATE_LOGIC
sys.exit(0)
if __name__ == "__main__":
main()
PY_EOF
;;
esac
# Replace placeholders with actual values
# Use perl instead of sed for better multiline support
perl -i -pe "s/HOOK_NAME/$HOOK_NAME/g" "$SCRIPT_PATH"
perl -i -pe "s/DESCRIPTION/Generated hook for $EVENT_TYPE event/g" "$SCRIPT_PATH"
# Insert template-specific logic by replacing the placeholder line
# Generate language-appropriate code based on the language choice
insert_template_logic() {
local template=$1
local lang=$2
local replacement=""
case "$lang" in
bash)
case "$template" in
validation)
replacement='# Validation logic\nif [[ -z "$TOOL_NAME" ]]; then\n exit 0\nfi\n\n# Add your validation rules here\n# Example: Block dangerous operations\necho "✓ Validation passed"'
;;
formatting)
replacement='# Formatting logic\nif [[ -z "$FILE_PATH" ]]; then\n exit 0\nfi\n\n# Add your formatting commands here\necho "✓ Formatting completed"'
;;
logging)
replacement='# Logging logic\nLOG_FILE="${CLAUDE_PROJECT_DIR:-.}/.claude/hook-logs.log"\nTIMESTAMP=$(date -Iseconds)\necho "[$TIMESTAMP] Event: $HOOK_EVENT, Tool: $TOOL_NAME" >> "$LOG_FILE"'
;;
notification)
replacement='# Notification logic\n# Add your notification code here\necho "✓ Notification sent"'
;;
context)
replacement='# Context injection logic\necho "## Additional Context"\necho "Hook Event: $HOOK_EVENT"\necho "Tool: $TOOL_NAME"\necho "Timestamp: $(date -Iseconds)"'
;;
esac
;;
typescript)
case "$template" in
validation)
replacement='// Validation logic\n\tif (!toolName) {\n\t\tprocess.exit(0);\n\t}\n\n\t// Add your validation rules here\n\t// Example: Block dangerous operations\n\tstdout.write("✓ Validation passed\\n");\n\tprocess.exit(0);'
;;
formatting)
replacement='// Formatting logic\n\tif (!filePath) {\n\t\tprocess.exit(0);\n\t}\n\n\t// Add your formatting commands here\n\tstdout.write("✓ Formatting completed\\n");\n\tprocess.exit(0);'
;;
logging)
replacement='// Logging logic\n\tconst logFile = `${process.env.CLAUDE_PROJECT_DIR || "."}/.claude/hook-logs.log`;\n\tconst timestamp = new Date().toISOString();\n\tconst logLine = `[${timestamp}] Event: ${hookEvent}, Tool: ${toolName}\\n`;\n\tfs.appendFileSync(logFile, logLine);\n\tprocess.exit(0);'
;;
notification)
replacement='// Notification logic\n\t// Add your notification code here\n\tstdout.write("✓ Notification sent\\n");\n\tprocess.exit(0);'
;;
context)
replacement='// Context injection logic\n\tstdout.write("## Additional Context\\n");\n\tstdout.write(`Hook Event: ${hookEvent}\\n`);\n\tstdout.write(`Tool: ${toolName}\\n`);\n\tstdout.write(`Timestamp: ${new Date().toISOString()}\\n`);\n\tprocess.exit(0);'
;;
esac
;;
python)
case "$template" in
validation)
replacement='# Validation logic\n if not tool_name:\n sys.exit(0)\n\n # Add your validation rules here\n # Example: Block dangerous operations\n print("✓ Validation passed")'
;;
formatting)
replacement='# Formatting logic\n if not file_path:\n sys.exit(0)\n\n # Add your formatting commands here\n print("✓ Formatting completed")'
;;
logging)
replacement='# Logging logic\n import os\n from datetime import datetime\n log_file = os.path.join(os.environ.get("CLAUDE_PROJECT_DIR", "."), ".claude", "hook-logs.log")\n timestamp = datetime.now().isoformat()\n with open(log_file, "a") as f:\n f.write(f"[{timestamp}] Event: {hook_event}, Tool: {tool_name}\\n")'
;;
notification)
replacement='# Notification logic\n # Add your notification code here\n print("✓ Notification sent")'
;;
context)
replacement='# Context injection logic\n from datetime import datetime\n print("## Additional Context")\n print(f"Hook Event: {hook_event}")\n print(f"Tool: {tool_name}")\n print(f"Timestamp: {datetime.now().isoformat()}")'
;;
esac
;;
esac
if [[ -n "$replacement" ]]; then
perl -i -pe "BEGIN{undef \$/;} s/# TEMPLATE_LOGIC/$replacement/smg" "$SCRIPT_PATH"
fi
}
insert_template_logic "$TEMPLATE_TYPE" "$LANGUAGE"
# Make script executable
chmod +x "$SCRIPT_PATH"
echo -e "${GREEN}✓ Created hook script: $SCRIPT_PATH${NC}"
# Generate hook configuration
echo
echo -e "${BLUE}Hook configuration to add to $CONFIG_FILE:${NC}"
echo
# Construct relative path if in project
if [[ "$OUTPUT_DIR" == ".claude/hooks" ]] || [[ "$OUTPUT_DIR" == "$PWD/.claude/hooks" ]]; then
COMMAND_PATH="\$CLAUDE_PROJECT_DIR/.claude/hooks/$HOOK_NAME.$SCRIPT_EXT"
elif [[ "$OUTPUT_DIR" == "$HOME/.claude/hooks" ]]; then
COMMAND_PATH="$HOME/.claude/hooks/$HOOK_NAME.$SCRIPT_EXT"
else
COMMAND_PATH="$SCRIPT_PATH"
fi
cat << EOF
{
"hooks": {
"$EVENT_TYPE": [
{
"matcher": "$MATCHER",
"hooks": [
{
"type": "command",
"command": "$COMMAND_PATH",
"timeout": $TIMEOUT
}
]
}
]
}
}
EOF
echo
echo -e "${BLUE}Next steps:${NC}"
echo " 1. Edit $SCRIPT_PATH to add your hook logic"
echo " 2. Test the hook: ./scripts/test-hook.ts $SCRIPT_PATH"
echo " 3. Add configuration to $CONFIG_FILE"
echo " 4. Validate config: ./scripts/validate-hook.sh $CONFIG_FILE"
echo
# Offer to add to config
if [[ -f "$CONFIG_FILE" ]]; then
read -r -p "Add this hook to $CONFIG_FILE now? (y/N): " ADD_CONFIG
if [[ "$ADD_CONFIG" =~ ^[Yy]$ ]]; then
# Check if hooks already exist in config
if jq -e '.hooks' "$CONFIG_FILE" >/dev/null 2>&1; then
# Hooks exist, merge
TEMP_FILE=$(mktemp)
jq --arg event "$EVENT_TYPE" \
--arg matcher "$MATCHER" \
--arg cmd "$COMMAND_PATH" \
--argjson timeout "$TIMEOUT" \
'.hooks[$event] += [{
"matcher": $matcher,
"hooks": [{
"type": "command",
"command": $cmd,
"timeout": $timeout
}]
}]' "$CONFIG_FILE" > "$TEMP_FILE"
mv "$TEMP_FILE" "$CONFIG_FILE"
else
# No hooks, create new structure
TEMP_FILE=$(mktemp)
jq --arg event "$EVENT_TYPE" \
--arg matcher "$MATCHER" \
--arg cmd "$COMMAND_PATH" \
--argjson timeout "$TIMEOUT" \
'. + {
"hooks": {
($event): [{
"matcher": $matcher,
"hooks": [{
"type": "command",
"command": $cmd,
"timeout": $timeout
}]
}]
}
}' "$CONFIG_FILE" > "$TEMP_FILE"
mv "$TEMP_FILE" "$CONFIG_FILE"
fi
echo -e "${GREEN}✓ Added hook to $CONFIG_FILE${NC}"
fi
else
echo -e "${YELLOW}Note: Config file $CONFIG_FILE doesn't exist yet${NC}"
echo "You'll need to create it and add the hook configuration manually"
fi
@@ -0,0 +1,482 @@
#!/usr/bin/env bun
/**
* test-hook.ts - Test Claude Code hook scripts with sample input
*
* Usage:
* ./test-hook.ts <hook-script> [options]
* ./test-hook.ts validate-bash.sh --event PreToolUse --tool Bash
*/
import { existsSync, statSync } from "node:fs";
import { resolve } from "node:path";
import { spawn } from "bun";
// ANSI colors
const colors = {
red: "\x1b[0;31m",
green: "\x1b[0;32m",
yellow: "\x1b[1;33m",
blue: "\x1b[0;34m",
reset: "\x1b[0m",
};
/**
* JSON input structure for Claude Code hooks.
*/
interface HookInput {
session_id: string;
transcript_path: string;
cwd: string;
hook_event_name: string;
tool_name?: string;
tool_input?: Record<string, unknown>;
reason?: string;
}
/**
* Options for testing a hook script.
*/
interface TestOptions {
event: string;
tool?: string;
filePath?: string;
content?: string;
command?: string;
reason?: string;
customInput?: string;
verbose: boolean;
timeout: number;
}
// Show help
function showHelp() {
console.log(`Usage: test-hook.ts <hook-script> [options]
Test Claude Code hook scripts with sample input.
Arguments:
hook-script Path to hook script to test
Options:
-e, --event Event type (default: PreToolUse)
PreToolUse, PostToolUse, UserPromptSubmit, Notification,
Stop, SubagentStop, PreCompact, SessionStart, SessionEnd
-t, --tool Tool name (e.g., Write, Edit, Bash)
-f, --file File path for tool input
-c, --content File content for Write tool
--command Command for Bash tool
-r, --reason Reason for session events
--input Custom JSON input (overrides all other options)
--timeout Timeout in milliseconds (default: 5000)
-v, --verbose Verbose output
-h, --help Show this help
Examples:
# Test PreToolUse hook with Bash tool
./test-hook.ts validate-bash.sh -e PreToolUse -t Bash --command "rm -rf /"
# Test PostToolUse hook with Write tool
./test-hook.ts format-code.sh -e PostToolUse -t Write -f test.ts -c "console.log('test');"
# Test with custom JSON input
./test-hook.ts my-hook.sh --input '{"tool_name":"Write","tool_input":{"file_path":"test.txt"}}'
# Test SessionStart hook
./test-hook.ts welcome.sh -e SessionStart -r startup
Event Types:
PreToolUse - Before tool execution (can block)
PostToolUse - After tool completes successfully
UserPromptSubmit - When user submits prompt
Notification - When notification sent
Stop - When main agent finishes
SubagentStop - When subagent finishes
PreCompact - Before conversation compacts
SessionStart - When session starts/resumes
SessionEnd - When session ends
`);
}
// Parse arguments
function parseArgs(): { scriptPath: string; options: TestOptions } {
const args = process.argv.slice(2);
if (args.length === 0 || args.includes("-h") || args.includes("--help")) {
showHelp();
process.exit(0);
}
const scriptPath = args[0];
const options: TestOptions = {
event: "PreToolUse",
verbose: false,
timeout: 5000,
};
for (let i = 1; i < args.length; i++) {
const arg = args[i];
const next = args[i + 1];
switch (arg) {
case "-e":
case "--event":
options.event = next;
i++;
break;
case "-t":
case "--tool":
options.tool = next;
i++;
break;
case "-f":
case "--file":
options.filePath = next;
i++;
break;
case "-c":
case "--content":
options.content = next;
i++;
break;
case "--command":
options.command = next;
i++;
break;
case "-r":
case "--reason":
options.reason = next;
i++;
break;
case "--input":
options.customInput = next;
i++;
break;
case "--timeout": {
const parsed = parseInt(next, 10);
if (Number.isNaN(parsed) || parsed <= 0) {
console.error(
`${colors.red}Error: --timeout must be a positive number${colors.reset}`,
);
process.exit(1);
}
options.timeout = parsed;
i++;
break;
}
case "-v":
case "--verbose":
options.verbose = true;
break;
default:
console.error(
`${colors.red}Error: Unknown option ${arg}${colors.reset}`,
);
process.exit(1);
}
}
return { scriptPath, options };
}
// Generate sample input based on event and options
function generateInput(options: TestOptions): HookInput {
const baseInput: HookInput = {
session_id: `test-session-${Date.now()}`,
transcript_path: "/tmp/transcript.jsonl",
cwd: process.cwd(),
hook_event_name: options.event,
};
// Add tool-specific fields
if (options.tool) {
baseInput.tool_name = options.tool;
// Generate appropriate tool_input
switch (options.tool) {
case "Write":
baseInput.tool_input = {
file_path: options.filePath || "/tmp/test-file.txt",
content: options.content || "Test content",
};
break;
case "Edit":
baseInput.tool_input = {
file_path: options.filePath || "/tmp/test-file.txt",
old_string: "old",
new_string: "new",
replace_all: false,
};
break;
case "Read":
baseInput.tool_input = {
file_path: options.filePath || "/tmp/test-file.txt",
offset: 0,
limit: 2000,
};
break;
case "Bash":
baseInput.tool_input = {
command: options.command || "echo 'test'",
description: "Test bash command",
};
break;
case "Grep":
baseInput.tool_input = {
pattern: "test",
path: options.filePath || ".",
};
break;
default:
baseInput.tool_input = {
file_path: options.filePath,
};
}
}
// Add reason for session events
if (["SessionStart", "SessionEnd", "PreCompact"].includes(options.event)) {
baseInput.reason = options.reason || "test";
}
return baseInput;
}
// Run hook script with input
async function runHook(
scriptPath: string,
input: HookInput,
timeout: number,
verbose: boolean,
): Promise<{
exitCode: number | null;
stdout: string;
stderr: string;
timedOut: boolean;
}> {
const inputJson = JSON.stringify(input, null, 2);
if (verbose) {
console.log(`${colors.blue}Input JSON:${colors.reset}`);
console.log(inputJson);
console.log();
}
// Spawn process
const proc = spawn({
cmd: [scriptPath],
stdin: "pipe",
stdout: "pipe",
stderr: "pipe",
env: {
...process.env,
CLAUDE_PROJECT_DIR: process.cwd(),
},
});
// Write input to stdin
proc.stdin.write(inputJson);
proc.stdin.end();
let timedOut = false;
const timeoutId = setTimeout(() => {
timedOut = true;
proc.kill();
}, timeout);
try {
const result = await proc.exited;
clearTimeout(timeoutId);
const stdout = await new Response(proc.stdout).text();
const stderr = await new Response(proc.stderr).text();
return {
exitCode: timedOut ? null : result,
stdout,
stderr,
timedOut,
};
} catch (error) {
clearTimeout(timeoutId);
throw error;
}
}
// Main function
async function main() {
const { scriptPath, options } = parseArgs();
// Validate script path
const resolvedPath = resolve(scriptPath);
if (!existsSync(resolvedPath)) {
console.error(
`${colors.red}Error: Script not found: ${scriptPath}${colors.reset}`,
);
process.exit(1);
}
// Check if executable
const stats = statSync(resolvedPath);
if (!(stats.mode & 0o111)) {
console.error(
`${colors.yellow}Warning: Script is not executable${colors.reset}`,
);
console.error(`Run: chmod +x ${scriptPath}`);
console.log();
}
console.log(
`${colors.blue}Testing hook script: ${scriptPath}${colors.reset}`,
);
console.log();
// Generate or parse input
let input: HookInput;
if (options.customInput) {
try {
input = JSON.parse(options.customInput);
console.log(`${colors.blue}Using custom input${colors.reset}`);
} catch (_error) {
console.error(
`${colors.red}Error: Invalid JSON in --input${colors.reset}`,
);
process.exit(1);
}
} else {
input = generateInput(options);
console.log(
`${colors.blue}Generated input for ${options.event}${options.tool ? ` with ${options.tool}` : ""}${colors.reset}`,
);
}
if (options.verbose) {
console.log();
}
// Run hook
console.log(`${colors.blue}Running hook...${colors.reset}`);
console.log();
const startTime = Date.now();
let result: Awaited<ReturnType<typeof runHook>>;
try {
result = await runHook(
resolvedPath,
input,
options.timeout,
options.verbose,
);
} catch (error) {
console.error(`${colors.red}✗ Hook execution failed${colors.reset}`);
console.error(error);
process.exit(1);
}
const duration = Date.now() - startTime;
// Display results
console.log(`${colors.blue}=== Results ===${colors.reset}`);
console.log();
// Handle timeout
if (result.timedOut) {
console.log(
`${colors.red}✗ Hook timed out after ${options.timeout}ms${colors.reset}`,
);
console.log();
}
// Exit code
const exitCode = result.exitCode ?? -1;
let exitCodeColor = colors.green;
let exitCodeLabel = "Success";
if (result.timedOut) {
exitCodeColor = colors.red;
exitCodeLabel = "Timeout (killed)";
} else if (exitCode === 2) {
exitCodeColor = colors.red;
exitCodeLabel = "Blocked (exit 2)";
} else if (exitCode !== 0) {
exitCodeColor = colors.yellow;
exitCodeLabel = "Warning (non-zero)";
}
console.log(
`${exitCodeColor}Exit Code: ${exitCode} - ${exitCodeLabel}${colors.reset}`,
);
console.log(`Duration: ${duration}ms`);
console.log();
// Stdout
if (result.stdout) {
console.log(`${colors.green}Stdout:${colors.reset}`);
console.log(result.stdout);
console.log();
} else {
console.log(`${colors.blue}Stdout: (empty)${colors.reset}`);
console.log();
}
// Stderr
if (result.stderr) {
console.log(`${colors.yellow}Stderr:${colors.reset}`);
console.log(result.stderr);
console.log();
} else {
console.log(`${colors.blue}Stderr: (empty)${colors.reset}`);
console.log();
}
// Summary
console.log(`${colors.blue}=== Summary ===${colors.reset}`);
console.log();
if (exitCode === 0) {
console.log(`${colors.green}✓ Hook executed successfully${colors.reset}`);
if (result.stdout) {
console.log(" Stdout will be shown to user");
}
} else if (exitCode === 2) {
console.log(
`${colors.red}✗ Hook blocked operation (exit 2)${colors.reset}`,
);
if (result.stderr) {
console.log(" Stderr will be shown to Claude");
}
} else {
console.log(
`${colors.yellow}⚠ Hook returned warning (exit ${exitCode})${colors.reset}`,
);
if (result.stderr) {
console.log(" Stderr will be shown to user");
}
}
// Performance warning
if (duration > 1000) {
console.log(
`${colors.yellow}⚠ Hook took ${duration}ms (>1s)${colors.reset}`,
);
console.log(" Consider optimizing for faster execution");
}
console.log();
// Exit with same code as hook
process.exit(exitCode === 0 ? 0 : 1);
}
// Run main
main().catch((error) => {
console.error(`${colors.red}Fatal error:${colors.reset}`, error);
process.exit(1);
});
@@ -0,0 +1,363 @@
#!/usr/bin/env bash
# validate-hook.sh - Validate Claude Code hook configuration and scripts
set -euo pipefail
# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
# Counters
ERRORS=0
WARNINGS=0
# Help text
show_help() {
cat << EOF
Usage: $(basename "$0") <config-file> [options]
Validate Claude Code hook configuration and referenced scripts.
Arguments:
config-file Path to settings.json file with hooks configuration
Options:
-s, --strict Strict mode (warnings become errors)
-q, --quiet Only show errors and warnings
--check-scripts Verify all referenced scripts exist and are executable
-h, --help Show this help
Examples:
# Validate project hooks
$(basename "$0") .claude/settings.json
# Validate personal hooks
$(basename "$0") ~/.claude/settings.json
# Strict validation with script checking
$(basename "$0") .claude/settings.json --strict --check-scripts
Exit Codes:
0 - Validation passed
1 - Validation failed with errors
EOF
}
# Error reporting
error() {
((ERRORS++))
echo -e "${RED}✗ Error:${NC} $1"
}
warning() {
((WARNINGS++))
echo -e "${YELLOW}⚠ Warning:${NC} $1"
}
info() {
if [[ "$QUIET" == "false" ]]; then
echo -e "${BLUE} Info:${NC} $1"
fi
}
success() {
if [[ "$QUIET" == "false" ]]; then
echo -e "${GREEN}$1${NC}"
fi
}
# Parse arguments
CONFIG_FILE=""
STRICT=false
QUIET=false
CHECK_SCRIPTS=false
while [[ $# -gt 0 ]]; do
case $1 in
-h|--help)
show_help
exit 0
;;
-s|--strict)
STRICT=true
shift
;;
-q|--quiet)
QUIET=true
shift
;;
--check-scripts)
CHECK_SCRIPTS=true
shift
;;
-*)
echo -e "${RED}Error: Unknown option $1${NC}"
show_help
exit 1
;;
*)
CONFIG_FILE="$1"
shift
;;
esac
done
# Validate file argument
if [[ -z "$CONFIG_FILE" ]]; then
echo -e "${RED}Error: Config file required${NC}"
show_help
exit 1
fi
if [[ ! -f "$CONFIG_FILE" ]]; then
error "File not found: $CONFIG_FILE"
exit 1
fi
# Check if jq is installed
if ! command -v jq &>/dev/null; then
error "jq is not installed (required for JSON validation)"
exit 1
fi
# Start validation
if [[ "$QUIET" == "false" ]]; then
echo -e "${BLUE}Validating: $CONFIG_FILE${NC}"
echo
fi
# 1. Validate JSON syntax
if ! jq empty "$CONFIG_FILE" 2>/dev/null; then
error "Invalid JSON syntax"
exit 1
fi
success "JSON syntax valid"
# 2. Check if hooks exist in config
if ! jq -e '.hooks' "$CONFIG_FILE" >/dev/null 2>&1; then
info "No hooks configuration found (file is valid but has no hooks)"
exit 0
fi
success "Hooks configuration found"
# 3. Validate hook structure
VALID_EVENTS=(PreToolUse PostToolUse UserPromptSubmit Notification Stop SubagentStop PreCompact SessionStart SessionEnd)
# Get all event names
EVENTS=$(jq -r '.hooks | keys[]' "$CONFIG_FILE" 2>/dev/null || echo "")
if [[ -z "$EVENTS" ]]; then
warning "No events defined in hooks configuration"
fi
TOTAL_HOOKS=0
while IFS= read -r event; do
[[ -z "$event" ]] && continue
# Check if valid event
if [[ ! " ${VALID_EVENTS[*]} " =~ " ${event} " ]]; then
error "Invalid event type: $event (valid: ${VALID_EVENTS[*]})"
continue
fi
success "Event: $event"
# Validate event structure
EVENT_ARRAY=$(jq -c ".hooks.\"$event\"" "$CONFIG_FILE")
# Check if array
if ! echo "$EVENT_ARRAY" | jq -e 'type == "array"' >/dev/null 2>&1; then
error "Event '$event' must be an array"
continue
fi
# Get array length
ARRAY_LENGTH=$(echo "$EVENT_ARRAY" | jq 'length')
info " Found $ARRAY_LENGTH matcher(s) for $event"
# Validate each matcher entry
for ((i=0; i<ARRAY_LENGTH; i++)); do
MATCHER_ENTRY=$(echo "$EVENT_ARRAY" | jq -c ".[$i]")
# Check for matcher field
if ! echo "$MATCHER_ENTRY" | jq -e '.matcher' >/dev/null 2>&1; then
error " Entry $i in $event: missing 'matcher' field"
continue
fi
MATCHER=$(echo "$MATCHER_ENTRY" | jq -r '.matcher')
info " Matcher: $MATCHER"
# Validate matcher pattern
if [[ -z "$MATCHER" ]]; then
warning " Empty matcher pattern"
fi
# Check for hooks array
if ! echo "$MATCHER_ENTRY" | jq -e '.hooks' >/dev/null 2>&1; then
error " Entry $i in $event: missing 'hooks' array"
continue
fi
if ! echo "$MATCHER_ENTRY" | jq -e '.hooks | type == "array"' >/dev/null 2>&1; then
error " Entry $i in $event: 'hooks' must be an array"
continue
fi
# Validate each hook in the array
HOOKS_LENGTH=$(echo "$MATCHER_ENTRY" | jq '.hooks | length')
((TOTAL_HOOKS += HOOKS_LENGTH))
for ((j=0; j<HOOKS_LENGTH; j++)); do
HOOK=$(echo "$MATCHER_ENTRY" | jq -c ".hooks[$j]")
# Check type field
if ! echo "$HOOK" | jq -e '.type' >/dev/null 2>&1; then
error " Hook $j: missing 'type' field"
continue
fi
HOOK_TYPE=$(echo "$HOOK" | jq -r '.type')
if [[ "$HOOK_TYPE" != "command" ]]; then
error " Hook $j: invalid type '$HOOK_TYPE' (must be 'command')"
fi
# Check command field
if ! echo "$HOOK" | jq -e '.command' >/dev/null 2>&1; then
error " Hook $j: missing 'command' field"
continue
fi
COMMAND=$(echo "$HOOK" | jq -r '.command')
info " Command: $COMMAND"
# Check if command is empty
if [[ -z "$COMMAND" ]]; then
error " Hook $j: empty command"
continue
fi
# Check timeout
if echo "$HOOK" | jq -e '.timeout' >/dev/null 2>&1; then
TIMEOUT=$(echo "$HOOK" | jq -r '.timeout')
if ! [[ "$TIMEOUT" =~ ^[0-9]+$ ]]; then
error " Hook $j: timeout must be a number"
elif [[ "$TIMEOUT" -lt 1 ]]; then
error " Hook $j: timeout must be at least 1 second"
elif [[ "$TIMEOUT" -gt 300 ]]; then
warning " Hook $j: timeout is very long ($TIMEOUT seconds)"
fi
else
info " Using default timeout (30 seconds)"
fi
# Check script if enabled
if [[ "$CHECK_SCRIPTS" == "true" ]]; then
# Extract script path (handle variables)
SCRIPT_PATH="$COMMAND"
# Replace common variables
SCRIPT_PATH="${SCRIPT_PATH//\$CLAUDE_PROJECT_DIR/$(dirname "$CONFIG_FILE")}"
SCRIPT_PATH="${SCRIPT_PATH//\$\{CLAUDE_PROJECT_DIR\}/$(dirname "$CONFIG_FILE")}"
SCRIPT_PATH="${SCRIPT_PATH//\~/~}"
# Extract first argument (script path)
SCRIPT_PATH=$(echo "$SCRIPT_PATH" | awk '{print $1}')
# Remove quotes
SCRIPT_PATH="${SCRIPT_PATH//\"/}"
SCRIPT_PATH="${SCRIPT_PATH//\'/}"
# Check if script exists
if [[ -f "$SCRIPT_PATH" ]]; then
success " Script exists: $SCRIPT_PATH"
# Check if executable
if [[ ! -x "$SCRIPT_PATH" ]]; then
warning " Script not executable: $SCRIPT_PATH (run: chmod +x $SCRIPT_PATH)"
else
success " Script is executable"
fi
# Check shebang
FIRST_LINE=$(head -n 1 "$SCRIPT_PATH")
if [[ ! "$FIRST_LINE" =~ ^#! ]]; then
warning " Script missing shebang line"
fi
elif [[ "$SCRIPT_PATH" =~ ^\$ ]] || [[ "$SCRIPT_PATH" =~ ^(echo|printf|cat|true|false|test|:)$ ]]; then
info " Inline/built-in command, skipping script check"
else
warning " Script not found: $SCRIPT_PATH"
fi
fi
done
done
echo
done <<< "$EVENTS"
# Summary
info "Total hooks validated: $TOTAL_HOOKS"
echo
# 4. Check for common issues
# Duplicate matchers
DUPLICATE_MATCHERS=$(jq -r '.hooks | to_entries[] | .key as $event | .value[] | .matcher | "\($event):\(.)"' "$CONFIG_FILE" | sort | uniq -c | awk '$1 > 1 {print $0}')
if [[ -n "$DUPLICATE_MATCHERS" ]]; then
warning "Duplicate matchers found (may cause hooks to run multiple times):"
echo "$DUPLICATE_MATCHERS" | while read -r line; do
warning " $line"
done
fi
# Very long commands
LONG_COMMANDS=$(jq -r '.hooks | to_entries[] | .value[] | .hooks[] | .command | select(length > 200)' "$CONFIG_FILE" 2>/dev/null || echo "")
if [[ -n "$LONG_COMMANDS" ]]; then
warning "Very long commands found (consider using script files):"
echo "$LONG_COMMANDS" | while IFS= read -r cmd; do
warning " ${cmd:0:100}..."
done
fi
# Hooks without timeout
HOOKS_WITHOUT_TIMEOUT=$(jq '[.hooks | to_entries[] | .value[] | .hooks[] | select(.timeout == null)] | length' "$CONFIG_FILE")
if [[ "$HOOKS_WITHOUT_TIMEOUT" -gt 0 ]]; then
info "$HOOKS_WITHOUT_TIMEOUT hook(s) using default timeout"
fi
# PreToolUse hooks with long timeouts
SLOW_PRE_HOOKS=$(jq -r '.hooks.PreToolUse[]? | .hooks[] | select(.timeout > 10) | .command' "$CONFIG_FILE" 2>/dev/null || echo "")
if [[ -n "$SLOW_PRE_HOOKS" ]]; then
warning "PreToolUse hooks with timeout >10s (may slow down operations):"
echo "$SLOW_PRE_HOOKS" | while IFS= read -r cmd; do
warning " $cmd"
done
fi
# Convert warnings to errors in strict mode
if [[ "$STRICT" == "true" && $WARNINGS -gt 0 ]]; then
ERRORS=$((ERRORS + WARNINGS))
WARNINGS=0
fi
# Final summary
echo
if [[ $ERRORS -eq 0 && $WARNINGS -eq 0 ]]; then
echo -e "${GREEN}✓ Validation passed!${NC}"
exit 0
elif [[ $ERRORS -eq 0 ]]; then
echo -e "${YELLOW}⚠ Validation passed with $WARNINGS warning(s)${NC}"
exit 0
else
echo -e "${RED}✗ Validation failed with $ERRORS error(s)${NC}"
if [[ $WARNINGS -gt 0 ]]; then
echo -e "${YELLOW} and $WARNINGS warning(s)${NC}"
fi
exit 1
fi