claude-code-hooks

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Claude Code Hooks — Meta Reference

Claude Code 钩子 — 元参考文档

This skill provides the definitive reference for creating Claude Code hooks. Use this when building automation that triggers on Claude Code events.

本技能提供了创建Claude Code钩子的权威参考。在构建基于Claude Code事件触发的自动化流程时，请使用本文档。

When to Use This Skill

何时使用该技能

Building event-driven automation for Claude Code
Creating PreToolUse guards to block dangerous commands
Implementing PostToolUse formatters, linters, or auditors
Adding Stop hooks for testing or notifications
Setting up SessionStart/SessionEnd for environment management
Integrating Claude Code with CI/CD pipelines (headless mode)

为Claude Code构建事件驱动的自动化流程
创建PreToolUse守卫以阻止危险命令
实现PostToolUse格式化工具、代码检查工具或审计工具
添加用于测试或通知的Stop钩子
设置SessionStart/SessionEnd用于环境管理
将Claude Code与CI/CD流水线集成（无头模式）

Quick Reference

快速参考

Event	Trigger	Use Case
`SessionStart`	Session begins/resumes	Initialize environment
`UserPromptSubmit`	User submits prompt	Preprocess/validate input
`PreToolUse`	Before tool execution	Validate, block dangerous commands
`PermissionRequest`	Permission dialog shown	Auto-allow/deny permissions
`PostToolUse`	After tool succeeds	Format, audit, notify
`PostToolUseFailure`	After tool fails	Capture failures, add guidance
`SubagentStart`	Subagent spawns	Inspect subagent metadata
`Stop`	When Claude finishes	Run tests, summarize
`SubagentStop`	Subagent finishes	Verify subagent completion
`Notification`	On notifications	Alert integrations
`PreCompact`	Before context compaction	Preserve critical context
`Setup`	`--init` / `--maintenance`	Initialize repo/env
`SessionEnd`	Session ends	Cleanup, save state

事件	触发条件	使用场景
`SessionStart`	会话开始/恢复	初始化环境
`UserPromptSubmit`	用户提交提示词	预处理/验证输入
`PreToolUse`	工具执行前	验证、阻止危险命令
`PermissionRequest`	显示权限对话框时	自动允许/拒绝权限
`PostToolUse`	工具执行成功后	格式化、审计、发送通知
`PostToolUseFailure`	工具执行失败后	捕获失败信息、添加指导
`SubagentStart`	子Agent启动时	检查子Agent元数据
`Stop`	Claude完成任务时	运行测试、生成总结
`SubagentStop`	子Agent完成任务时	验证子Agent的完成情况
`Notification`	收到通知时	与告警系统集成
`PreCompact`	上下文压缩前	保留关键上下文
`Setup`	执行 `--init` / `--maintenance` 命令时	初始化仓库/环境
`SessionEnd`	会话结束时	清理环境、保存状态

Hook Structure

钩子结构

text

.claude/hooks/
├── pre-tool-validate.sh
├── post-tool-format.sh
├── post-tool-audit.sh
├── stop-run-tests.sh
└── session-start-init.sh

text

.claude/hooks/
├── pre-tool-validate.sh
├── post-tool-format.sh
├── post-tool-audit.sh
├── stop-run-tests.sh
└── session-start-init.sh

Configuration

配置

settings.json

json

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/post-tool-format.sh"
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/pre-tool-validate.sh"
          }
        ]
      }
    ],
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/stop-run-tests.sh"
          }
        ]
      }
    ]
  }
}

json

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/post-tool-format.sh"
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/pre-tool-validate.sh"
          }
        ]
      }
    ],
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/stop-run-tests.sh"
          }
        ]
      }
    ]
  }
}

Execution Model (Jan 2026)

执行模型（2026年1月）

Hooks receive a JSON payload via stdin (treat it as untrusted input) and run with your user permissions (outside the Bash tool sandbox).
Default timeout is 60s per hook command; all matching hooks run in parallel; identical commands are deduplicated.

钩子通过标准输入接收JSON负载（需将其视为不可信输入），并以你的用户权限运行（在Bash工具沙箱之外）。
默认超时时间为每个钩子命令60秒；所有匹配的钩子并行运行；相同的命令会被去重。

Hook Input (stdin)

钩子输入（标准输入）

json

{
  "hook_event_name": "PreToolUse",
  "tool_name": "Bash",
  "tool_input": {
    "command": "ls -la"
  }
}

json

{
  "hook_event_name": "PreToolUse",
  "tool_name": "Bash",
  "tool_input": {
    "command": "ls -la"
  }
}

Environment Variables (shell)

环境变量（Shell）

Variable	Description
`CLAUDE_PROJECT_DIR`	Absolute project root where Claude Code started
`CLAUDE_PLUGIN_ROOT`	Plugin root (plugin hooks only)
`CLAUDE_CODE_REMOTE`	`"true"` in remote/web environments; empty/local otherwise
`CLAUDE_ENV_FILE`	File path to persist `export ...` lines (available in SessionStart; check docs for Setup support)

变量	描述
`CLAUDE_PROJECT_DIR`	Claude Code启动时的项目根目录绝对路径
`CLAUDE_PLUGIN_ROOT`	插件根目录（仅适用于插件钩子）
`CLAUDE_CODE_REMOTE`	在远程/网页环境中为 `"true"` ；本地环境为空
`CLAUDE_ENV_FILE`	用于保存 `export ...` 行的文件路径（SessionStart事件中可用；请查阅文档了解Setup事件的支持情况）

Exit Codes

退出码

Code	Meaning	Notes
`0`	Success	JSON written to stdout is parsed for structured control
`2`	Blocking error	`stderr` becomes the message; JSON in stdout is ignored
Other	Non-blocking error	Execution continues; `stderr` is visible in verbose mode

Stdout injection note: for

UserPromptSubmit

SessionStart

, and

Setup

, non-JSON stdout (exit 0) is injected into Claude’s context; most other events show stdout only in verbose mode.

代码	含义	说明
`0`	成功	写入标准输出的JSON会被解析以进行结构化控制
`2`	阻塞性错误	`stderr` 内容会作为提示信息；标准输出中的JSON会被忽略
其他	非阻塞性错误	执行会继续； `stderr` 内容仅在详细模式下可见

标准输出注入说明：对于

UserPromptSubmit

、

SessionStart

和

Setup

事件，非JSON格式的标准输出（退出码0）会被注入到Claude的上下文中；大多数其他事件仅在详细模式下显示标准输出。

Decision Control + Input Modification (v2.0.10+)

决策控制 + 输入修改（v2.0.10+）

PreToolUse hooks can allow/deny/ask and optionally modify the tool input via

updatedInput

PreToolUse钩子可以允许/拒绝/询问，并可通过

updatedInput

选择性地修改工具输入。

Hook Output Schema

钩子输出 Schema

json

{
  "hookSpecificOutput": {
    "hookEventName": "PreToolUse",
    "permissionDecision": "allow",
    "permissionDecisionReason": "Reason shown to user (and to Claude on deny)",
    "updatedInput": { "command": "echo 'modified'" },
    "additionalContext": "Extra context added before tool runs"
  }
}

Note: older

decision

reason

fields are deprecated; prefer the

hookSpecificOutput.*

fields.

json

{
  "hookSpecificOutput": {
    "hookEventName": "PreToolUse",
    "permissionDecision": "allow",
    "permissionDecisionReason": "显示给用户的理由（拒绝时也会显示给Claude）",
    "updatedInput": { "command": "echo 'modified'" },
    "additionalContext": "工具运行前添加的额外上下文"
  }
}

注意：旧版的

decision

reason

字段已被弃用；建议使用

hookSpecificOutput.*

字段。

Example: Redirect Sensitive File Edits

示例：重定向敏感文件编辑

bash

#!/bin/bash
set -euo pipefail

INPUT="$(cat)"
FILE_PATH="$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')"

bash

#!/bin/bash
set -euo pipefail

INPUT="$(cat)"
FILE_PATH="$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')"

Redirect package-lock.json edits to /dev/null

if [[ "$FILE_PATH" == *"package-lock.json" ]]; then UPDATED_INPUT="$(echo "$INPUT" | jq -c '.tool_input | .file_path = "/dev/null"')" jq -cn --argjson updatedInput "$UPDATED_INPUT" '{ hookSpecificOutput: { hookEventName: "PreToolUse", permissionDecision: "allow", permissionDecisionReason: "Redirected write to /dev/null", updatedInput: $updatedInput } }' exit 0 fi

echo '{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow"}}'

undefined

echo '{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow"}}'

undefined

Example: Strip Sensitive Files from Git Add

示例：从Git Add中移除敏感文件

bash

#!/bin/bash
set -euo pipefail

INPUT="$(cat)"
TOOL_NAME="$(echo "$INPUT" | jq -r '.tool_name')"
CMD="$(echo "$INPUT" | jq -r '.tool_input.command // empty')"

if [[ "$TOOL_NAME" == "Bash" && "$CMD" =~ ^git[[:space:]]+add ]]; then
  # Remove .env files from staging
  SAFE_CMD="$(echo "$CMD" | sed 's/\.env[^ ]*//g')"
  if [[ "$SAFE_CMD" != "$CMD" ]]; then
    echo '{}' | jq -cn --arg cmd "$SAFE_CMD" '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "allow",
        permissionDecisionReason: "Removed .env from git add",
        updatedInput: { command: $cmd }
      }
    }'
    exit 0
  fi
fi

echo '{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow"}}'

bash

#!/bin/bash
set -euo pipefail

INPUT="$(cat)"
TOOL_NAME="$(echo "$INPUT" | jq -r '.tool_name')"
CMD="$(echo "$INPUT" | jq -r '.tool_input.command // empty')"

if [[ "$TOOL_NAME" == "Bash" && "$CMD" =~ ^git[[:space:]]+add ]]; then
  # Remove .env files from staging
  SAFE_CMD="$(echo "$CMD" | sed 's/\.env[^ ]*//g')"
  if [[ "$SAFE_CMD" != "$CMD" ]]; then
    echo '{}' | jq -cn --arg cmd "$SAFE_CMD" '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "allow",
        permissionDecisionReason: "Removed .env from git add",
        updatedInput: { command: $cmd }
      }
    }'
    exit 0
  fi
fi

echo '{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow"}}'

Prompt-Based Hooks

基于提示词的钩子

For complex decisions, use LLM-evaluated hooks (

type: "prompt"

) instead of bash scripts. They are most useful for

Stop

and

SubagentStop

decisions.

对于复杂决策，使用LLM评估的钩子（

type: "prompt"

）替代bash脚本。它们在

Stop

和

SubagentStop

决策中最为有用。

Configuration

配置

json

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "prompt",
            "prompt": "Evaluate whether Claude should stop. Context JSON: $ARGUMENTS. Return {\"ok\": true} if all tasks are complete, otherwise {\"ok\": false, \"reason\": \"what remains\"}.",
            "timeout": 30
          }
        ]
      }
    ]
  }
}

json

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "prompt",
            "prompt": "Evaluate whether Claude should stop. Context JSON: $ARGUMENTS. Return {\"ok\": true} if all tasks are complete, otherwise {\"ok\": false, \"reason\": \"what remains\"}.",
            "timeout": 30
          }
        ]
      }
    ]
  }
}

Response Schema

响应 Schema

Allow:
```
{"ok": true}
```

Block:

{"ok": false, "reason": "Explanation shown to Claude"}

允许：
```
{"ok": true}
```

阻止：

{"ok": false, "reason": "显示给Claude的解释"}

Combining Command and Prompt Hooks

组合命令型和提示词型钩子

Use command hooks for fast, deterministic checks. Use prompt hooks for nuanced decisions:

json

{
  "Stop": [
    {
      "hooks": [
        { "type": "command", "command": ".claude/hooks/quick-check.sh" },
        { "type": "prompt", "prompt": "Verify code quality meets standards" }
      ]
    }
  ]
}

使用命令型钩子进行快速、确定性检查。使用提示词型钩子进行精细化决策：

json

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          { "type": "command", "command": ".claude/hooks/quick-check.sh" },
          { "type": "prompt", "prompt": "Verify code quality meets standards" }
        ]
      }
    ]
  }
}

Hook Templates

钩子模板

Pre-Tool Validation

工具执行前验证

bash

#!/bin/bash
set -euo pipefail

INPUT="$(cat)"
TOOL_NAME="$(echo "$INPUT" | jq -r '.tool_name')"
CMD="$(echo "$INPUT" | jq -r '.tool_input.command // empty')"

if [[ "$TOOL_NAME" == "Bash" ]]; then
  # Block rm -rf /
  if echo "$CMD" | grep -qE 'rm\s+-rf\s+/'; then
    echo '{}' | jq -cn '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "deny",
        permissionDecisionReason: "Dangerous rm command detected"
      }
    }'
    exit 0
  fi

  # Block force push to main
  if echo "$CMD" | grep -qE 'git\s+push.*--force.*(main|master)'; then
    echo '{}' | jq -cn '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "deny",
        permissionDecisionReason: "Force push to main/master not allowed"
      }
    }'
    exit 0
  fi

  # Soft-warning: possible credential exposure
  if echo "$CMD" | grep -qE '(password|secret|api_key)\s*='; then
    echo '{}' | jq -cn '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "ask",
        permissionDecisionReason: "Possible credential exposure in command",
        additionalContext: "Command may include a secret. Confirm intent and avoid committing secrets."
      }
    }'
    exit 0
  fi
fi

exit 0

bash

#!/bin/bash
set -euo pipefail

INPUT="$(cat)"
TOOL_NAME="$(echo "$INPUT" | jq -r '.tool_name')"
CMD="$(echo "$INPUT" | jq -r '.tool_input.command // empty')"

if [[ "$TOOL_NAME" == "Bash" ]]; then
  # Block rm -rf /
  if echo "$CMD" | grep -qE 'rm\s+-rf\s+/'; then
    echo '{}' | jq -cn '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "deny",
        permissionDecisionReason: "Dangerous rm command detected"
      }
    }'
    exit 0
  fi

  # Block force push to main
  if echo "$CMD" | grep -qE 'git\s+push.*--force.*(main|master)'; then
    echo '{}' | jq -cn '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "deny",
        permissionDecisionReason: "Force push to main/master not allowed"
      }
    }'
    exit 0
  fi

  # Soft-warning: possible credential exposure
  if echo "$CMD" | grep -qE '(password|secret|api_key)\s*='; then
    echo '{}' | jq -cn '{
      hookSpecificOutput: {
        hookEventName: "PreToolUse",
        permissionDecision: "ask",
        permissionDecisionReason: "Possible credential exposure in command",
        additionalContext: "Command may include a secret. Confirm intent and avoid committing secrets."
      }
    }'
    exit 0
  fi
fi

exit 0

Post-Tool Formatting

工具执行后格式化

bash

#!/bin/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')"

if [[ "$TOOL_NAME" =~ ^(Edit|Write)$ && -n "$FILE_PATH" && -f "$FILE_PATH" ]]; then
  case "$FILE_PATH" in
    *.js|*.ts|*.jsx|*.tsx|*.json|*.md)
      npx prettier --write "$FILE_PATH" 2>/dev/null || true
      ;;
    *.py)
      ruff format "$FILE_PATH" 2>/dev/null || true
      ;;
    *.go)
      gofmt -w "$FILE_PATH" 2>/dev/null || true
      ;;
    *.rs)
      rustfmt "$FILE_PATH" 2>/dev/null || true
      ;;
  esac
fi

exit 0

bash

#!/bin/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')"

if [[ "$TOOL_NAME" =~ ^(Edit|Write)$ && -n "$FILE_PATH" && -f "$FILE_PATH" ]]; then
  case "$FILE_PATH" in
    *.js|*.ts|*.jsx|*.tsx|*.json|*.md)
      npx prettier --write "$FILE_PATH" 2>/dev/null || true
      ;;
    *.py)
      ruff format "$FILE_PATH" 2>/dev/null || true
      ;;
    *.go)
      gofmt -w "$FILE_PATH" 2>/dev/null || true
      ;;
    *.rs)
      rustfmt "$FILE_PATH" 2>/dev/null || true
      ;;
  esac
fi

exit 0

Post-Tool Security Audit

工具执行后安全审计

bash

#!/bin/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')"

if [[ "$TOOL_NAME" =~ ^(Edit|Write)$ && -n "$FILE_PATH" && -f "$FILE_PATH" ]]; then
  # Check for hardcoded secrets
  if grep -qE '(password|secret|api_key|token)\s*[:=]\s*["\x27][^"\x27]+["\x27]' "$FILE_PATH"; then
    echo "WARNING: Possible hardcoded secret in $FILE_PATH" >&2
  fi

  # Check for console.log in production code
  if [[ "$FILE_PATH" =~ \.(ts|js|tsx|jsx)$ ]] && grep -q 'console.log' "$FILE_PATH"; then
    echo "NOTE: console.log found in $FILE_PATH" >&2
  fi
fi

exit 0

bash

#!/bin/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')"

if [[ "$TOOL_NAME" =~ ^(Edit|Write)$ && -n "$FILE_PATH" && -f "$FILE_PATH" ]]; then
  # Check for hardcoded secrets
  if grep -qE '(password|secret|api_key|token)\s*[:=]\s*["\x27][^"\x27]+["\x27]' "$FILE_PATH"; then
    echo "WARNING: Possible hardcoded secret in $FILE_PATH" >&2
  fi

  # Check for console.log in production code
  if [[ "$FILE_PATH" =~ \.(ts|js|tsx|jsx)$ ]] && grep -q 'console.log' "$FILE_PATH"; then
    echo "NOTE: console.log found in $FILE_PATH" >&2
  fi
fi

exit 0

Stop Hook (Run Tests)

Stop钩子（运行测试）

bash

#!/bin/bash
set -euo pipefail

bash

#!/bin/bash
set -euo pipefail

Run tests after Claude finishes

cd "$CLAUDE_PROJECT_DIR"

Detect test framework

if [[ -f "package.json" ]]; then if grep -q '"vitest"' package.json; then npm run test 2>&1 | head -50 elif grep -q '"jest"' package.json; then npm test 2>&1 | head -50 fi elif [[ -f "pytest.ini" ]] || [[ -f "pyproject.toml" ]]; then pytest --tb=short 2>&1 | head -50 fi

exit 0

undefined

exit 0

undefined

Session Start

会话开始

bash

#!/bin/bash
set -euo pipefail

cd "$CLAUDE_PROJECT_DIR"

bash

#!/bin/bash
set -euo pipefail

cd "$CLAUDE_PROJECT_DIR"

Check git status

echo "=== Git Status ===" git status --short

Check for uncommitted changes

if ! git diff --quiet; then echo "WARNING: Uncommitted changes detected" fi

Verify dependencies

if [[ -f "package.json" ]]; then if [[ ! -d "node_modules" ]]; then echo "NOTE: node_modules missing, run npm install" fi fi

exit 0

---

if [[ -f "package.json" ]]; then if [[ ! -d "node_modules" ]]; then echo "NOTE: node_modules missing, run npm install" fi fi

exit 0

---

Matchers

匹配器

Matchers filter which tool triggers the hook:

Exact match:
```
Write
```
matches only the Write tool
Regex:
```
Edit|Write
```
or
```
Notebook.*
```
Match all:
```
*
```
(also works with
```
""
```
or omitted matcher)

匹配器用于筛选触发钩子的工具：

精确匹配：
```
Write
```
仅匹配Write工具
正则匹配：
```
Edit|Write
```
或
```
Notebook.*
```
匹配所有：
```
*
```
（也可使用
```
""
```
或省略matcher字段）

Security Best Practices

安全最佳实践

text

HOOK SECURITY CHECKLIST

[ ] Validate all inputs with regex
[ ] Quote all variables: "$VAR" not $VAR
[ ] Use absolute paths
[ ] No eval with untrusted input
[ ] Set -euo pipefail at top
[ ] Keep hooks fast (<1 second)
[ ] Log actions for audit
[ ] Test manually before deploying

text

HOOK SECURITY CHECKLIST

[ ] Validate all inputs with regex
[ ] Quote all variables: "$VAR" not $VAR
[ ] Use absolute paths
[ ] No eval with untrusted input
[ ] Set -euo pipefail at top
[ ] Keep hooks fast (<1 second)
[ ] Log actions for audit
[ ] Test manually before deploying

Hook Composition

钩子组合

Multiple Hooks on Same Event

同一事件的多个钩子

json

{
  "PostToolUse": [
    {
      "matcher": "Edit|Write",
      "hooks": [
        { "type": "command", "command": ".claude/hooks/format.sh" },
        { "type": "command", "command": ".claude/hooks/audit.sh" },
        { "type": "command", "command": ".claude/hooks/notify.sh" }
      ]
    }
  ]
}

All matching hooks run in parallel. If you need strict ordering (format → lint → test), make one wrapper script that runs them sequentially.

json

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          { "type": "command", "command": ".claude/hooks/format.sh" },
          { "type": "command", "command": ".claude/hooks/audit.sh" },
          { "type": "command", "command": ".claude/hooks/notify.sh" }
        ]
      }
    ]
  }
}

所有匹配的钩子会并行运行。如果需要严格的执行顺序（格式化 → 代码检查 → 测试），请创建一个包装脚本按顺序运行它们。

Debugging Hooks

调试钩子

bash

undefined

bash

undefined

Test a PostToolUse hook manually (stdin JSON)

export CLAUDE_PROJECT_DIR="$(pwd)" echo '{"hook_event_name":"PostToolUse","tool_name":"Edit","tool_input":{"file_path":"'"$(pwd)"'/src/app.ts"}}'
| bash .claude/hooks/post-tool-format.sh

Check exit code

echo $?

---

echo $?

---

claude-code-hooks

Original

Translation

Claude Code Hooks — Meta Reference

Claude Code 钩子 — 元参考文档

When to Use This Skill

何时使用该技能

Quick Reference

快速参考

Hook Structure

钩子结构

Configuration

配置

settings.json

settings.json

Execution Model (Jan 2026)

执行模型（2026年1月）

Hook Input (stdin)

钩子输入（标准输入）

Environment Variables (shell)

环境变量（Shell）

Exit Codes

退出码

Decision Control + Input Modification (v2.0.10+)

决策控制 + 输入修改（v2.0.10+）

Hook Output Schema

钩子输出 Schema

Example: Redirect Sensitive File Edits

示例：重定向敏感文件编辑

Redirect package-lock.json edits to /dev/null

Redirect package-lock.json edits to /dev/null

Example: Strip Sensitive Files from Git Add

示例：从Git Add中移除敏感文件

Prompt-Based Hooks

基于提示词的钩子

Configuration

配置

Response Schema

响应 Schema

Combining Command and Prompt Hooks

组合命令型和提示词型钩子

Hook Templates

钩子模板

Pre-Tool Validation

工具执行前验证

Post-Tool Formatting

工具执行后格式化

Post-Tool Security Audit

工具执行后安全审计

Stop Hook (Run Tests)

Stop钩子（运行测试）

Run tests after Claude finishes

Run tests after Claude finishes

Detect test framework

Detect test framework

Session Start

会话开始

Check git status

Check git status

Check for uncommitted changes

Check for uncommitted changes

Verify dependencies

Verify dependencies

Matchers

匹配器

Security Best Practices

安全最佳实践

Hook Composition

钩子组合

Multiple Hooks on Same Event

同一事件的多个钩子

Debugging Hooks

调试钩子

Test a PostToolUse hook manually (stdin JSON)

Test a PostToolUse hook manually (stdin JSON)

Check exit code

Check exit code

Navigation

导航

Resources