1> ## Documentation Index
2> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt
3> Use this file to discover all available pages before exploring further.
4
1# Hooks reference5# Hooks reference
2 6
3> This page provides reference documentation for implementing hooks in Claude Code.7> Reference for Claude Code hook events, configuration schema, JSON input/output formats, exit codes, async hooks, prompt hooks, and MCP tool hooks.
4 8
5<Tip>9<Tip>
6 For a quickstart guide with examples, see [Get started with Claude Code hooks](/en/hooks-guide).10 For a quickstart guide with examples, see [Automate workflows with hooks](/en/hooks-guide).
7</Tip>11</Tip>
8 12
9## Configuration13Hooks are user-defined shell commands or LLM prompts that execute automatically at specific points in Claude Code's lifecycle. Use this reference to look up event schemas, configuration options, JSON input/output formats, and advanced features like async hooks and MCP tool hooks. If you're setting up hooks for the first time, start with the [guide](/en/hooks-guide) instead.
14
15## Hook lifecycle
16
17Hooks fire at specific points during a Claude Code session. When an event fires and a matcher matches, Claude Code passes JSON context about the event to your hook handler. For command hooks, this arrives on stdin. Your handler can then inspect the input, take action, and optionally return a decision. Some events fire once per session, while others fire repeatedly inside the agentic loop:
10 18
11Claude Code hooks are configured in your [settings files](/en/settings):19<div style={{maxWidth: "500px", margin: "0 auto"}}>
20 <Frame>
21 <img src="https://mintcdn.com/claude-code/rsuu-ovdPNos9Dnn/images/hooks-lifecycle.svg?fit=max&auto=format&n=rsuu-ovdPNos9Dnn&q=85&s=ce5f1225339bbccdfbb52e99205db912" alt="Hook lifecycle diagram showing the sequence of hooks from SessionStart through the agentic loop to SessionEnd, with WorktreeCreate and WorktreeRemove as standalone setup and teardown events" data-og-width="520" width="520" data-og-height="1020" height="1020" data-path="images/hooks-lifecycle.svg" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/claude-code/rsuu-ovdPNos9Dnn/images/hooks-lifecycle.svg?w=280&fit=max&auto=format&n=rsuu-ovdPNos9Dnn&q=85&s=7c7143c65492c1beb6bc66f5d206ba15 280w, https://mintcdn.com/claude-code/rsuu-ovdPNos9Dnn/images/hooks-lifecycle.svg?w=560&fit=max&auto=format&n=rsuu-ovdPNos9Dnn&q=85&s=dafaebf8f789f94edbf6bd66853c69df 560w, https://mintcdn.com/claude-code/rsuu-ovdPNos9Dnn/images/hooks-lifecycle.svg?w=840&fit=max&auto=format&n=rsuu-ovdPNos9Dnn&q=85&s=2caa51d2d95596f1f80b92e3f5f534fa 840w, https://mintcdn.com/claude-code/rsuu-ovdPNos9Dnn/images/hooks-lifecycle.svg?w=1100&fit=max&auto=format&n=rsuu-ovdPNos9Dnn&q=85&s=614def559f34f9b0c1dec93739d96b64 1100w, https://mintcdn.com/claude-code/rsuu-ovdPNos9Dnn/images/hooks-lifecycle.svg?w=1650&fit=max&auto=format&n=rsuu-ovdPNos9Dnn&q=85&s=ca45b85fdd8b2da81c69d12c453230cb 1650w, https://mintcdn.com/claude-code/rsuu-ovdPNos9Dnn/images/hooks-lifecycle.svg?w=2500&fit=max&auto=format&n=rsuu-ovdPNos9Dnn&q=85&s=7fd92d6b9713493f59962c9f295c9d2f 2500w" />
22 </Frame>
23</div>
12 24
13* `~/.claude/settings.json` - User settings25The table below summarizes when each event fires. The [Hook events](#hook-events) section documents the full input schema and decision control options for each one.
14* `.claude/settings.json` - Project settings
15* `.claude/settings.local.json` - Local project settings (not committed)
16* Enterprise managed policy settings
17 26
18### Structure27| Event | When it fires |
28| :------------------- | :---------------------------------------------------------------------------------------------------------- |
29| `SessionStart` | When a session begins or resumes |
30| `UserPromptSubmit` | When you submit a prompt, before Claude processes it |
31| `PreToolUse` | Before a tool call executes. Can block it |
32| `PermissionRequest` | When a permission dialog appears |
33| `PostToolUse` | After a tool call succeeds |
34| `PostToolUseFailure` | After a tool call fails |
35| `Notification` | When Claude Code sends a notification |
36| `SubagentStart` | When a subagent is spawned |
37| `SubagentStop` | When a subagent finishes |
38| `Stop` | When Claude finishes responding |
39| `TeammateIdle` | When an [agent team](/en/agent-teams) teammate is about to go idle |
40| `TaskCompleted` | When a task is being marked as completed |
41| `ConfigChange` | When a configuration file changes during a session |
42| `WorktreeCreate` | When a worktree is being created via `--worktree` or `isolation: "worktree"`. Replaces default git behavior |
43| `WorktreeRemove` | When a worktree is being removed, either at session exit or when a subagent finishes |
44| `PreCompact` | Before context compaction |
45| `SessionEnd` | When a session terminates |
19 46
20Hooks are organized by matchers, where each matcher can have multiple hooks:47### How a hook resolves
48
49To see how these pieces fit together, consider this `PreToolUse` hook that blocks destructive shell commands. The hook runs `block-rm.sh` before every Bash tool call:
21 50
22```json theme={null}51```json theme={null}
23{52{
24 "hooks": {53 "hooks": {
25 "EventName": [54 "PreToolUse": [
26 {55 {
27 "matcher": "ToolPattern",56 "matcher": "Bash",
28 "hooks": [57 "hooks": [
29 {58 {
30 "type": "command",59 "type": "command",
31 "command": "your-command-here"60 "command": ".claude/hooks/block-rm.sh"
32 }61 }
33 ]62 ]
34 }63 }
37}66}
38```67```
39 68
40* **matcher**: Pattern to match tool names, case-sensitive (only applicable for69The script reads the JSON input from stdin, extracts the command, and returns a `permissionDecision` of `"deny"` if it contains `rm -rf`:
41 `PreToolUse` and `PostToolUse`)
42 * Simple strings match exactly: `Write` matches only the Write tool
43 * Supports regex: `Edit|Write` or `Notebook.*`
44 * Use `*` to match all tools. You can also use empty string (`""`) or leave
45 `matcher` blank.
46* **hooks**: Array of hooks to execute when the pattern matches
47 * `type`: Hook execution type - `"command"` for bash commands or `"prompt"` for LLM-based evaluation
48 * `command`: (For `type: "command"`) The bash command to execute (can use `$CLAUDE_PROJECT_DIR` environment variable)
49 * `prompt`: (For `type: "prompt"`) The prompt to send to the LLM for evaluation
50 * `timeout`: (Optional) How long a hook should run, in seconds, before canceling that specific hook
51
52For events like `UserPromptSubmit`, `Notification`, `Stop`, and `SubagentStop`
53that don't use matchers, you can omit the matcher field:
54 70
55```json theme={null}71```bash theme={null}
56{72#!/bin/bash
57 "hooks": {73# .claude/hooks/block-rm.sh
58 "UserPromptSubmit": [74COMMAND=$(jq -r '.tool_input.command')
59 {75
60 "hooks": [76if echo "$COMMAND" | grep -q 'rm -rf'; then
61 {77 jq -n '{
62 "type": "command",78 hookSpecificOutput: {
63 "command": "/path/to/prompt-validator.py"79 hookEventName: "PreToolUse",
64 }80 permissionDecision: "deny",
65 ]81 permissionDecisionReason: "Destructive command blocked by hook"
66 }
67 ]
68 }82 }
69}83 }'
84else
85 exit 0 # allow the command
86fi
70```87```
71 88
72### Project-Specific Hook Scripts89Now suppose Claude Code decides to run `Bash "rm -rf /tmp/build"`. Here's what happens:
73 90
74You can use the environment variable `CLAUDE_PROJECT_DIR` (only available when91<Frame>
75Claude Code spawns the hook command) to reference scripts stored in your project,92 <img src="https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=5bb890134390ecd0581477cf41ef730b" alt="Hook resolution flow: PreToolUse event fires, matcher checks for Bash match, hook handler runs, result returns to Claude Code" data-og-width="780" width="780" data-og-height="290" height="290" data-path="images/hook-resolution.svg" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?w=280&fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=5dcaecd24c260b8a90365d74e2c1fcda 280w, https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?w=560&fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=c03d91c279f01d92e58ddd70fdbe66f2 560w, https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?w=840&fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=1be57a4819cbb949a5ea9d08a05c9ecd 840w, https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?w=1100&fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=0e9dd1807dc7a5c56011d0889b0d5208 1100w, https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?w=1650&fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=69496ac02e70fabfece087ba31a1dcfc 1650w, https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?w=2500&fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=a012346cb46a33b86580348802055267 2500w" />
76ensuring they work regardless of Claude's current directory:93</Frame>
77 94
78```json theme={null}95<Steps>
79{96 <Step title="Event fires">
80 "hooks": {97 The `PreToolUse` event fires. Claude Code sends the tool input as JSON on stdin to the hook:
81 "PostToolUse": [98
82 {99 ```json theme={null}
83 "matcher": "Write|Edit",100 { "tool_name": "Bash", "tool_input": { "command": "rm -rf /tmp/build" }, ... }
84 "hooks": [101 ```
102 </Step>
103
104 <Step title="Matcher checks">
105 The matcher `"Bash"` matches the tool name, so `block-rm.sh` runs. If you omit the matcher or use `"*"`, the hook runs on every occurrence of the event. Hooks only skip when a matcher is defined and doesn't match.
106 </Step>
107
108 <Step title="Hook handler runs">
109 The script extracts `"rm -rf /tmp/build"` from the input and finds `rm -rf`, so it prints a decision to stdout:
110
111 ```json theme={null}
85 {112 {
86 "type": "command",113 "hookSpecificOutput": {
87 "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/check-style.sh"114 "hookEventName": "PreToolUse",
88 }115 "permissionDecision": "deny",
89 ]116 "permissionDecisionReason": "Destructive command blocked by hook"
90 }117 }
91 ]
92 }118 }
93}119 ```
94```120
121 If the command had been safe (like `npm test`), the script would hit `exit 0` instead, which tells Claude Code to allow the tool call with no further action.
122 </Step>
123
124 <Step title="Claude Code acts on the result">
125 Claude Code reads the JSON decision, blocks the tool call, and shows Claude the reason.
126 </Step>
127</Steps>
128
129The [Configuration](#configuration) section below documents the full schema, and each [hook event](#hook-events) section documents what input your command receives and what output it can return.
130
131## Configuration
132
133Hooks are defined in JSON settings files. The configuration has three levels of nesting:
134
1351. Choose a [hook event](#hook-events) to respond to, like `PreToolUse` or `Stop`
1362. Add a [matcher group](#matcher-patterns) to filter when it fires, like "only for the Bash tool"
1373. Define one or more [hook handlers](#hook-handler-fields) to run when matched
95 138
96### Plugin hooks139See [How a hook resolves](#how-a-hook-resolves) above for a complete walkthrough with an annotated example.
97 140
98[Plugins](/en/plugins) can provide hooks that integrate seamlessly with your user and project hooks. Plugin hooks are automatically merged with your configuration when plugins are enabled.141<Note>
142 This page uses specific terms for each level: **hook event** for the lifecycle point, **matcher group** for the filter, and **hook handler** for the shell command, prompt, or agent that runs. "Hook" on its own refers to the general feature.
143</Note>
144
145### Hook locations
146
147Where you define a hook determines its scope:
148
149| Location | Scope | Shareable |
150| :--------------------------------------------------------- | :---------------------------- | :--------------------------------- |
151| `~/.claude/settings.json` | All your projects | No, local to your machine |
152| `.claude/settings.json` | Single project | Yes, can be committed to the repo |
153| `.claude/settings.local.json` | Single project | No, gitignored |
154| Managed policy settings | Organization-wide | Yes, admin-controlled |
155| [Plugin](/en/plugins) `hooks/hooks.json` | When plugin is enabled | Yes, bundled with the plugin |
156| [Skill](/en/skills) or [agent](/en/sub-agents) frontmatter | While the component is active | Yes, defined in the component file |
157
158For details on settings file resolution, see [settings](/en/settings). Enterprise administrators can use `allowManagedHooksOnly` to block user, project, and plugin hooks. See [Hook configuration](/en/settings#hook-configuration).
159
160### Matcher patterns
161
162The `matcher` field is a regex string that filters when hooks fire. Use `"*"`, `""`, or omit `matcher` entirely to match all occurrences. Each event type matches on a different field:
99 163
100**How plugin hooks work**:164| Event | What the matcher filters | Example matcher values |
165| :---------------------------------------------------------------------------------------------- | :------------------------ | :--------------------------------------------------------------------------------- |
166| `PreToolUse`, `PostToolUse`, `PostToolUseFailure`, `PermissionRequest` | tool name | `Bash`, `Edit\|Write`, `mcp__.*` |
167| `SessionStart` | how the session started | `startup`, `resume`, `clear`, `compact` |
168| `SessionEnd` | why the session ended | `clear`, `logout`, `prompt_input_exit`, `bypass_permissions_disabled`, `other` |
169| `Notification` | notification type | `permission_prompt`, `idle_prompt`, `auth_success`, `elicitation_dialog` |
170| `SubagentStart` | agent type | `Bash`, `Explore`, `Plan`, or custom agent names |
171| `PreCompact` | what triggered compaction | `manual`, `auto` |
172| `SubagentStop` | agent type | same values as `SubagentStart` |
173| `ConfigChange` | configuration source | `user_settings`, `project_settings`, `local_settings`, `policy_settings`, `skills` |
174| `UserPromptSubmit`, `Stop`, `TeammateIdle`, `TaskCompleted`, `WorktreeCreate`, `WorktreeRemove` | no matcher support | always fires on every occurrence |
101 175
102* Plugin hooks are defined in the plugin's `hooks/hooks.json` file or in a file given by a custom path to the `hooks` field.176The matcher is a regex, so `Edit|Write` matches either tool and `Notebook.*` matches any tool starting with Notebook. The matcher runs against a field from the [JSON input](#hook-input-and-output) that Claude Code sends to your hook on stdin. For tool events, that field is `tool_name`. Each [hook event](#hook-events) section lists the full set of matcher values and the input schema for that event.
103* When a plugin is enabled, its hooks are merged with user and project hooks
104* Multiple hooks from different sources can respond to the same event
105* Plugin hooks use the `${CLAUDE_PLUGIN_ROOT}` environment variable to reference plugin files
106 177
107**Example plugin hook configuration**:178This example runs a linting script only when Claude writes or edits a file:
108 179
109```json theme={null}180```json theme={null}
110{181{
111 "description": "Automatic code formatting",
112 "hooks": {182 "hooks": {
113 "PostToolUse": [183 "PostToolUse": [
114 {184 {
115 "matcher": "Write|Edit",185 "matcher": "Edit|Write",
116 "hooks": [186 "hooks": [
117 {187 {
118 "type": "command",188 "type": "command",
119 "command": "${CLAUDE_PLUGIN_ROOT}/scripts/format.sh",189 "command": "/path/to/lint-check.sh"
120 "timeout": 30
121 }190 }
122 ]191 ]
123 }192 }
126}195}
127```196```
128 197
129<Note>198`UserPromptSubmit`, `Stop`, `TeammateIdle`, `TaskCompleted`, `WorktreeCreate`, and `WorktreeRemove` don't support matchers and always fire on every occurrence. If you add a `matcher` field to these events, it is silently ignored.
130 Plugin hooks use the same format as regular hooks with an optional `description` field to explain the hook's purpose.
131</Note>
132
133<Note>
134 Plugin hooks run alongside your custom hooks. If multiple hooks match an event, they all execute in parallel.
135</Note>
136
137**Environment variables for plugins**:
138 199
139* `${CLAUDE_PLUGIN_ROOT}`: Absolute path to the plugin directory200#### Match MCP tools
140* `${CLAUDE_PROJECT_DIR}`: Project root directory (same as for project hooks)
141* All standard environment variables are available
142 201
143See the [plugin components reference](/en/plugins-reference#hooks) for details on creating plugin hooks.202[MCP](/en/mcp) server tools appear as regular tools in tool events (`PreToolUse`, `PostToolUse`, `PostToolUseFailure`, `PermissionRequest`), so you can match them the same way you match any other tool name.
144 203
145## Prompt-Based Hooks204MCP tools follow the naming pattern `mcp__<server>__<tool>`, for example:
146 205
147In addition to bash command hooks (`type: "command"`), Claude Code supports prompt-based hooks (`type: "prompt"`) that use an LLM to evaluate whether to allow or block an action. Prompt-based hooks are currently only supported for `Stop` and `SubagentStop` hooks, where they enable intelligent, context-aware decisions.206* `mcp__memory__create_entities`: Memory server's create entities tool
148 207* `mcp__filesystem__read_file`: Filesystem server's read file tool
149### How prompt-based hooks work208* `mcp__github__search_repositories`: GitHub server's search tool
150 209
151Instead of executing a bash command, prompt-based hooks:210Use regex patterns to target specific MCP tools or groups of tools:
152 211
1531. Send the hook input and your prompt to a fast LLM (Haiku)212* `mcp__memory__.*` matches all tools from the `memory` server
1542. The LLM responds with structured JSON containing a decision213* `mcp__.*__write.*` matches any tool containing "write" from any server
1553. Claude Code processes the decision automatically
156 214
157### Configuration215This example logs all memory server operations and validates write operations from any MCP server:
158 216
159```json theme={null}217```json theme={null}
160{218{
161 "hooks": {219 "hooks": {
162 "Stop": [220 "PreToolUse": [
163 {221 {
222 "matcher": "mcp__memory__.*",
164 "hooks": [223 "hooks": [
165 {224 {
166 "type": "prompt",225 "type": "command",
167 "prompt": "Evaluate if Claude should stop: $ARGUMENTS. Check if all tasks are complete."226 "command": "echo 'Memory operation initiated' >> ~/mcp-operations.log"
227 }
228 ]
229 },
230 {
231 "matcher": "mcp__.*__write.*",
232 "hooks": [
233 {
234 "type": "command",
235 "command": "/home/user/scripts/validate-mcp-write.py"
168 }236 }
169 ]237 ]
170 }238 }
173}241}
174```242```
175 243
176**Fields:**244### Hook handler fields
177 245
178* `type`: Must be `"prompt"`246Each object in the inner `hooks` array is a hook handler: the shell command, LLM prompt, or agent that runs when the matcher matches. There are three types:
179* `prompt`: The prompt text to send to the LLM
180 * Use `$ARGUMENTS` as a placeholder for the hook input JSON
181 * If `$ARGUMENTS` is not present, input JSON is appended to the prompt
182* `timeout`: (Optional) Timeout in seconds (default: 30 seconds)
183 247
184### Response schema248* **[Command hooks](#command-hook-fields)** (`type: "command"`): run a shell command. Your script receives the event's [JSON input](#hook-input-and-output) on stdin and communicates results back through exit codes and stdout.
249* **[Prompt hooks](#prompt-and-agent-hook-fields)** (`type: "prompt"`): send a prompt to a Claude model for single-turn evaluation. The model returns a yes/no decision as JSON. See [Prompt-based hooks](#prompt-based-hooks).
250* **[Agent hooks](#prompt-and-agent-hook-fields)** (`type: "agent"`): spawn a subagent that can use tools like Read, Grep, and Glob to verify conditions before returning a decision. See [Agent-based hooks](#agent-based-hooks).
185 251
186The LLM must respond with JSON containing:252#### Common fields
187 253
188```json theme={null}254These fields apply to all hook types:
189{
190 "decision": "approve" | "block",
191 "reason": "Explanation for the decision",
192 "continue": false, // Optional: stops Claude entirely
193 "stopReason": "Message shown to user", // Optional: custom stop message
194 "systemMessage": "Warning or context" // Optional: shown to user
195}
196```
197 255
198**Response fields:**256| Field | Required | Description |
257| :-------------- | :------- | :-------------------------------------------------------------------------------------------------------------------------------------------- |
258| `type` | yes | `"command"`, `"prompt"`, or `"agent"` |
259| `timeout` | no | Seconds before canceling. Defaults: 600 for command, 30 for prompt, 60 for agent |
260| `statusMessage` | no | Custom spinner message displayed while the hook runs |
261| `once` | no | If `true`, runs only once per session then is removed. Skills only, not agents. See [Hooks in skills and agents](#hooks-in-skills-and-agents) |
199 262
200* `decision`: `"approve"` allows the action, `"block"` prevents it263#### Command hook fields
201* `reason`: Explanation shown to Claude when decision is `"block"`
202* `continue`: (Optional) If `false`, stops Claude's execution entirely
203* `stopReason`: (Optional) Message shown when `continue` is false
204* `systemMessage`: (Optional) Additional message shown to the user
205 264
206### Supported hook events265In addition to the [common fields](#common-fields), command hooks accept these fields:
207 266
208Prompt-based hooks work with any hook event, but are most useful for:267| Field | Required | Description |
268| :-------- | :------- | :------------------------------------------------------------------------------------------------------------------ |
269| `command` | yes | Shell command to execute |
270| `async` | no | If `true`, runs in the background without blocking. See [Run hooks in the background](#run-hooks-in-the-background) |
209 271
210* **Stop**: Intelligently decide if Claude should continue working272#### Prompt and agent hook fields
211* **SubagentStop**: Evaluate if a subagent has completed its task
212* **UserPromptSubmit**: Validate user prompts with LLM assistance
213* **PreToolUse**: Make context-aware permission decisions
214 273
215### Example: Intelligent Stop hook274In addition to the [common fields](#common-fields), prompt and agent hooks accept these fields:
216 275
217```json theme={null}276| Field | Required | Description |
218{277| :------- | :------- | :------------------------------------------------------------------------------------------ |
278| `prompt` | yes | Prompt text to send to the model. Use `$ARGUMENTS` as a placeholder for the hook input JSON |
279| `model` | no | Model to use for evaluation. Defaults to a fast model |
280
281All matching hooks run in parallel, and identical handlers are deduplicated automatically. Handlers run in the current directory with Claude Code's environment. The `$CLAUDE_CODE_REMOTE` environment variable is set to `"true"` in remote web environments and not set in the local CLI.
282
283### Reference scripts by path
284
285Use environment variables to reference hook scripts relative to the project or plugin root, regardless of the working directory when the hook runs:
286
287* `$CLAUDE_PROJECT_DIR`: the project root. Wrap in quotes to handle paths with spaces.
288* `${CLAUDE_PLUGIN_ROOT}`: the plugin's root directory, for scripts bundled with a [plugin](/en/plugins).
289
290<Tabs>
291 <Tab title="Project scripts">
292 This example uses `$CLAUDE_PROJECT_DIR` to run a style checker from the project's `.claude/hooks/` directory after any `Write` or `Edit` tool call:
293
294 ```json theme={null}
295 {
219 "hooks": {296 "hooks": {
220 "Stop": [297 "PostToolUse": [
221 {298 {
299 "matcher": "Write|Edit",
222 "hooks": [300 "hooks": [
223 {301 {
224 "type": "prompt",302 "type": "command",
225 "prompt": "You are evaluating whether Claude should stop working. Context: $ARGUMENTS\n\nAnalyze the conversation and determine if:\n1. All user-requested tasks are complete\n2. Any errors need to be addressed\n3. Follow-up work is needed\n\nRespond with JSON: {\"decision\": \"approve\" or \"block\", \"reason\": \"your explanation\"}",303 "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/check-style.sh"
226 "timeout": 30
227 }304 }
228 ]305 ]
229 }306 }
230 ]307 ]
231 }308 }
232}309 }
233```310 ```
311 </Tab>
234 312
235### Example: SubagentStop with custom logic313 <Tab title="Plugin scripts">
314 Define plugin hooks in `hooks/hooks.json` with an optional top-level `description` field. When a plugin is enabled, its hooks merge with your user and project hooks.
236 315
237```json theme={null}316 This example runs a formatting script bundled with the plugin:
238{317
318 ```json theme={null}
319 {
320 "description": "Automatic code formatting",
239 "hooks": {321 "hooks": {
240 "SubagentStop": [322 "PostToolUse": [
241 {323 {
324 "matcher": "Write|Edit",
242 "hooks": [325 "hooks": [
243 {326 {
244 "type": "prompt",327 "type": "command",
245 "prompt": "Evaluate if this subagent should stop. Input: $ARGUMENTS\n\nCheck if:\n- The subagent completed its assigned task\n- Any errors occurred that need fixing\n- Additional context gathering is needed\n\nReturn: {\"decision\": \"approve\" or \"block\", \"reason\": \"explanation\"}"328 "command": "${CLAUDE_PLUGIN_ROOT}/scripts/format.sh",
329 "timeout": 30
246 }330 }
247 ]331 ]
248 }332 }
249 ]333 ]
250 }334 }
335 }
336 ```
337
338 See the [plugin components reference](/en/plugins-reference#hooks) for details on creating plugin hooks.
339 </Tab>
340</Tabs>
341
342### Hooks in skills and agents
343
344In addition to settings files and plugins, hooks can be defined directly in [skills](/en/skills) and [subagents](/en/sub-agents) using frontmatter. These hooks are scoped to the component's lifecycle and only run when that component is active.
345
346All hook events are supported. For subagents, `Stop` hooks are automatically converted to `SubagentStop` since that is the event that fires when a subagent completes.
347
348Hooks use the same configuration format as settings-based hooks but are scoped to the component's lifetime and cleaned up when it finishes.
349
350This skill defines a `PreToolUse` hook that runs a security validation script before each `Bash` command:
351
352```yaml theme={null}
353---
354name: secure-operations
355description: Perform operations with security checks
356hooks:
357 PreToolUse:
358 - matcher: "Bash"
359 hooks:
360 - type: command
361 command: "./scripts/security-check.sh"
362---
363```
364
365Agents use the same format in their YAML frontmatter.
366
367### The `/hooks` menu
368
369Type `/hooks` in Claude Code to open the interactive hooks manager, where you can view, add, and delete hooks without editing settings files directly. For a step-by-step walkthrough, see [Set up your first hook](/en/hooks-guide#set-up-your-first-hook) in the guide.
370
371Each hook in the menu is labeled with a bracket prefix indicating its source:
372
373* `[User]`: from `~/.claude/settings.json`
374* `[Project]`: from `.claude/settings.json`
375* `[Local]`: from `.claude/settings.local.json`
376* `[Plugin]`: from a plugin's `hooks/hooks.json`, read-only
377
378### Disable or remove hooks
379
380To remove a hook, delete its entry from the settings JSON file, or use the `/hooks` menu and select the hook to delete it.
381
382To temporarily disable all hooks without removing them, set `"disableAllHooks": true` in your settings file or use the toggle in the `/hooks` menu. There is no way to disable an individual hook while keeping it in the configuration.
383
384The `disableAllHooks` setting respects the managed settings hierarchy. If an administrator has configured hooks through managed policy settings, `disableAllHooks` set in user, project, or local settings cannot disable those managed hooks. Only `disableAllHooks` set at the managed settings level can disable managed hooks.
385
386Direct edits to hooks in settings files don't take effect immediately. Claude Code captures a snapshot of hooks at startup and uses it throughout the session. This prevents malicious or accidental hook modifications from taking effect mid-session without your review. If hooks are modified externally, Claude Code warns you and requires review in the `/hooks` menu before changes apply.
387
388## Hook input and output
389
390Hooks receive JSON data via stdin and communicate results through exit codes, stdout, and stderr. This section covers fields and behavior common to all events. Each event's section under [Hook events](#hook-events) includes its specific input schema and decision control options.
391
392### Common input fields
393
394All hook events receive these fields via stdin as JSON, in addition to event-specific fields documented in each [hook event](#hook-events) section:
395
396| Field | Description |
397| :---------------- | :----------------------------------------------------------------------------------------------------------------------------------------- |
398| `session_id` | Current session identifier |
399| `transcript_path` | Path to conversation JSON |
400| `cwd` | Current working directory when the hook is invoked |
401| `permission_mode` | Current [permission mode](/en/permissions#permission-modes): `"default"`, `"plan"`, `"acceptEdits"`, `"dontAsk"`, or `"bypassPermissions"` |
402| `hook_event_name` | Name of the event that fired |
403
404For example, a `PreToolUse` hook for a Bash command receives this on stdin:
405
406```json theme={null}
407{
408 "session_id": "abc123",
409 "transcript_path": "/home/user/.claude/projects/.../transcript.jsonl",
410 "cwd": "/home/user/my-project",
411 "permission_mode": "default",
412 "hook_event_name": "PreToolUse",
413 "tool_name": "Bash",
414 "tool_input": {
415 "command": "npm test"
416 }
251}417}
252```418```
253 419
254### Comparison with bash command hooks420The `tool_name` and `tool_input` fields are event-specific. Each [hook event](#hook-events) section documents the additional fields for that event.
255 421
256| Feature | Bash Command Hooks | Prompt-Based Hooks |422### Exit code output
257| --------------------- | ----------------------- | ------------------------------ |
258| **Execution** | Runs bash script | Queries LLM |
259| **Decision logic** | You implement in code | LLM evaluates context |
260| **Setup complexity** | Requires script file | Just configure prompt |
261| **Context awareness** | Limited to script logic | Natural language understanding |
262| **Performance** | Fast (local execution) | Slower (API call) |
263| **Use case** | Deterministic rules | Context-aware decisions |
264 423
265### Best practices424The exit code from your hook command tells Claude Code whether the action should proceed, be blocked, or be ignored.
266 425
267* **Be specific in prompts**: Clearly state what you want the LLM to evaluate426**Exit 0** means success. Claude Code parses stdout for [JSON output fields](#json-output). JSON output is only processed on exit 0. For most events, stdout is only shown in verbose mode (`Ctrl+O`). The exceptions are `UserPromptSubmit` and `SessionStart`, where stdout is added as context that Claude can see and act on.
268* **Include decision criteria**: List the factors the LLM should consider
269* **Test your prompts**: Verify the LLM makes correct decisions for your use cases
270* **Set appropriate timeouts**: Default is 30 seconds, adjust if needed
271* **Use for complex decisions**: Bash hooks are better for simple, deterministic rules
272 427
273See the [plugin components reference](/en/plugins-reference#hooks) for details on creating plugin hooks.428**Exit 2** means a blocking error. Claude Code ignores stdout and any JSON in it. Instead, stderr text is fed back to Claude as an error message. The effect depends on the event: `PreToolUse` blocks the tool call, `UserPromptSubmit` rejects the prompt, and so on. See [exit code 2 behavior](#exit-code-2-behavior-per-event) for the full list.
274 429
275## Hook Events430**Any other exit code** is a non-blocking error. stderr is shown in verbose mode (`Ctrl+O`) and execution continues.
276 431
277### PreToolUse432For example, a hook command script that blocks dangerous Bash commands:
433
434```bash theme={null}
435#!/bin/bash
436# Reads JSON input from stdin, checks the command
437command=$(jq -r '.tool_input.command' < /dev/stdin)
438
439if [[ "$command" == rm* ]]; then
440 echo "Blocked: rm commands are not allowed" >&2
441 exit 2 # Blocking error: tool call is prevented
442fi
278 443
279Runs after Claude creates tool parameters and before processing the tool call.444exit 0 # Success: tool call proceeds
445```
280 446
281**Common matchers:**447#### Exit code 2 behavior per event
448
449Exit code 2 is the way a hook signals "stop, don't do this." The effect depends on the event, because some events represent actions that can be blocked (like a tool call that hasn't happened yet) and others represent things that already happened or can't be prevented.
450
451| Hook event | Can block? | What happens on exit 2 |
452| :------------------- | :--------- | :---------------------------------------------------------------------------- |
453| `PreToolUse` | Yes | Blocks the tool call |
454| `PermissionRequest` | Yes | Denies the permission |
455| `UserPromptSubmit` | Yes | Blocks prompt processing and erases the prompt |
456| `Stop` | Yes | Prevents Claude from stopping, continues the conversation |
457| `SubagentStop` | Yes | Prevents the subagent from stopping |
458| `TeammateIdle` | Yes | Prevents the teammate from going idle (teammate continues working) |
459| `TaskCompleted` | Yes | Prevents the task from being marked as completed |
460| `ConfigChange` | Yes | Blocks the configuration change from taking effect (except `policy_settings`) |
461| `PostToolUse` | No | Shows stderr to Claude (tool already ran) |
462| `PostToolUseFailure` | No | Shows stderr to Claude (tool already failed) |
463| `Notification` | No | Shows stderr to user only |
464| `SubagentStart` | No | Shows stderr to user only |
465| `SessionStart` | No | Shows stderr to user only |
466| `SessionEnd` | No | Shows stderr to user only |
467| `PreCompact` | No | Shows stderr to user only |
468| `WorktreeCreate` | Yes | Any non-zero exit code causes worktree creation to fail |
469| `WorktreeRemove` | No | Failures are logged in debug mode only |
470
471### JSON output
472
473Exit codes let you allow or block, but JSON output gives you finer-grained control. Instead of exiting with code 2 to block, exit 0 and print a JSON object to stdout. Claude Code reads specific fields from that JSON to control behavior, including [decision control](#decision-control) for blocking, allowing, or escalating to the user.
282 474
283* `Task` - Subagent tasks (see [subagents documentation](/en/sub-agents))475<Note>
284* `Bash` - Shell commands476 You must choose one approach per hook, not both: either use exit codes alone for signaling, or exit 0 and print JSON for structured control. Claude Code only processes JSON on exit 0. If you exit 2, any JSON is ignored.
285* `Glob` - File pattern matching477</Note>
286* `Grep` - Content search
287* `Read` - File reading
288* `Edit` - File editing
289* `Write` - File writing
290* `WebFetch`, `WebSearch` - Web operations
291 478
292### PostToolUse479Your hook's stdout must contain only the JSON object. If your shell profile prints text on startup, it can interfere with JSON parsing. See [JSON validation failed](/en/hooks-guide#json-validation-failed) in the troubleshooting guide.
293 480
294Runs immediately after a tool completes successfully.481The JSON object supports three kinds of fields:
295 482
296Recognizes the same matcher values as PreToolUse.483* **Universal fields** like `continue` work across all events. These are listed in the table below.
484* **Top-level `decision` and `reason`** are used by some events to block or provide feedback.
485* **`hookSpecificOutput`** is a nested object for events that need richer control. It requires a `hookEventName` field set to the event name.
297 486
298### Notification487| Field | Default | Description |
488| :--------------- | :------ | :------------------------------------------------------------------------------------------------------------------------- |
489| `continue` | `true` | If `false`, Claude stops processing entirely after the hook runs. Takes precedence over any event-specific decision fields |
490| `stopReason` | none | Message shown to the user when `continue` is `false`. Not shown to Claude |
491| `suppressOutput` | `false` | If `true`, hides stdout from verbose mode output |
492| `systemMessage` | none | Warning message shown to the user |
299 493
300Runs when Claude Code sends notifications. Notifications are sent when:494To stop Claude entirely regardless of event type:
301 495
3021. Claude needs your permission to use a tool. Example: "Claude needs your496```json theme={null}
303 permission to use Bash"497{ "continue": false, "stopReason": "Build failed, fix errors before continuing" }
3042. The prompt input has been idle for at least 60 seconds. "Claude is waiting498```
305 for your input"
306 499
307### UserPromptSubmit500#### Decision control
308 501
309Runs when the user submits a prompt, before Claude processes it. This allows you502Not every event supports blocking or controlling behavior through JSON. The events that do each use a different set of fields to express that decision. Use this table as a quick reference before writing a hook:
310to add additional context based on the prompt/conversation, validate prompts, or
311block certain types of prompts.
312 503
313### Stop504| Events | Decision pattern | Key fields |
505| :---------------------------------------------------------------------------------- | :------------------- | :-------------------------------------------------------------------------- |
506| UserPromptSubmit, PostToolUse, PostToolUseFailure, Stop, SubagentStop, ConfigChange | Top-level `decision` | `decision: "block"`, `reason` |
507| TeammateIdle, TaskCompleted | Exit code only | Exit code 2 blocks the action, stderr is fed back as feedback |
508| PreToolUse | `hookSpecificOutput` | `permissionDecision` (allow/deny/ask), `permissionDecisionReason` |
509| PermissionRequest | `hookSpecificOutput` | `decision.behavior` (allow/deny) |
510| WorktreeCreate | stdout path | Hook prints absolute path to created worktree. Non-zero exit fails creation |
511| WorktreeRemove, Notification, SessionEnd, PreCompact | None | No decision control. Used for side effects like logging or cleanup |
314 512
315Runs when the main Claude Code agent has finished responding. Does not run if513Here are examples of each pattern in action:
316the stoppage occurred due to a user interrupt.
317 514
318### SubagentStop515<Tabs>
516 <Tab title="Top-level decision">
517 Used by `UserPromptSubmit`, `PostToolUse`, `PostToolUseFailure`, `Stop`, `SubagentStop`, and `ConfigChange`. The only value is `"block"`. To allow the action to proceed, omit `decision` from your JSON, or exit 0 without any JSON at all:
319 518
320Runs when a Claude Code subagent (Task tool call) has finished responding.519 ```json theme={null}
520 {
521 "decision": "block",
522 "reason": "Test suite must pass before proceeding"
523 }
524 ```
525 </Tab>
321 526
322### PreCompact527 <Tab title="PreToolUse">
528 Uses `hookSpecificOutput` for richer control: allow, deny, or escalate to the user. You can also modify tool input before it runs or inject additional context for Claude. See [PreToolUse decision control](#pretooluse-decision-control) for the full set of options.
323 529
324Runs before Claude Code is about to run a compact operation.530 ```json theme={null}
531 {
532 "hookSpecificOutput": {
533 "hookEventName": "PreToolUse",
534 "permissionDecision": "deny",
535 "permissionDecisionReason": "Database writes are not allowed"
536 }
537 }
538 ```
539 </Tab>
540
541 <Tab title="PermissionRequest">
542 Uses `hookSpecificOutput` to allow or deny a permission request on behalf of the user. When allowing, you can also modify the tool's input or apply permission rules so the user isn't prompted again. See [PermissionRequest decision control](#permissionrequest-decision-control) for the full set of options.
543
544 ```json theme={null}
545 {
546 "hookSpecificOutput": {
547 "hookEventName": "PermissionRequest",
548 "decision": {
549 "behavior": "allow",
550 "updatedInput": {
551 "command": "npm run lint"
552 }
553 }
554 }
555 }
556 ```
557 </Tab>
558</Tabs>
325 559
326**Matchers:**560For extended examples including Bash command validation, prompt filtering, and auto-approval scripts, see [What you can automate](/en/hooks-guide#what-you-can-automate) in the guide and the [Bash command validator reference implementation](https://github.com/anthropics/claude-code/blob/main/examples/hooks/bash_command_validator_example.py).
327 561
328* `manual` - Invoked from `/compact`562## Hook events
329* `auto` - Invoked from auto-compact (due to full context window)563
564Each event corresponds to a point in Claude Code's lifecycle where hooks can run. The sections below are ordered to match the lifecycle: from session setup through the agentic loop to session end. Each section describes when the event fires, what matchers it supports, the JSON input it receives, and how to control behavior through output.
330 565
331### SessionStart566### SessionStart
332 567
333Runs when Claude Code starts a new session or resumes an existing session (which568Runs when Claude Code starts a new session or resumes an existing session. Useful for loading development context like existing issues or recent changes to your codebase, or setting up environment variables. For static context that does not require a script, use [CLAUDE.md](/en/memory) instead.
334currently does start a new session under the hood). Useful for loading in569
335development context like existing issues or recent changes to your codebase, installing dependencies, or setting up environment variables.570SessionStart runs on every session, so keep these hooks fast.
571
572The matcher value corresponds to how the session was initiated:
573
574| Matcher | When it fires |
575| :-------- | :------------------------------------- |
576| `startup` | New session |
577| `resume` | `--resume`, `--continue`, or `/resume` |
578| `clear` | `/clear` |
579| `compact` | Auto or manual compaction |
580
581#### SessionStart input
582
583In addition to the [common input fields](#common-input-fields), SessionStart hooks receive `source`, `model`, and optionally `agent_type`. The `source` field indicates how the session started: `"startup"` for new sessions, `"resume"` for resumed sessions, `"clear"` after `/clear`, or `"compact"` after compaction. The `model` field contains the model identifier. If you start Claude Code with `claude --agent <name>`, an `agent_type` field contains the agent name.
584
585```json theme={null}
586{
587 "session_id": "abc123",
588 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
589 "cwd": "/Users/...",
590 "permission_mode": "default",
591 "hook_event_name": "SessionStart",
592 "source": "startup",
593 "model": "claude-sonnet-4-6"
594}
595```
596
597#### SessionStart decision control
598
599Any text your hook script prints to stdout is added as context for Claude. In addition to the [JSON output fields](#json-output) available to all hooks, you can return these event-specific fields:
336 600
337**Matchers:**601| Field | Description |
602| :------------------ | :------------------------------------------------------------------------ |
603| `additionalContext` | String added to Claude's context. Multiple hooks' values are concatenated |
338 604
339* `startup` - Invoked from startup605```json theme={null}
340* `resume` - Invoked from `--resume`, `--continue`, or `/resume`606{
341* `clear` - Invoked from `/clear`607 "hookSpecificOutput": {
342* `compact` - Invoked from auto or manual compact.608 "hookEventName": "SessionStart",
609 "additionalContext": "My additional context here"
610 }
611}
612```
343 613
344#### Persisting environment variables614#### Persist environment variables
345 615
346SessionStart hooks have access to the `CLAUDE_ENV_FILE` environment variable, which provides a file path where you can persist environment variables for subsequent bash commands.616SessionStart hooks have access to the `CLAUDE_ENV_FILE` environment variable, which provides a file path where you can persist environment variables for subsequent Bash commands.
347 617
348**Example: Setting individual environment variables**618To set individual environment variables, write `export` statements to `CLAUDE_ENV_FILE`. Use append (`>>`) to preserve variables set by other hooks:
349 619
350```bash theme={null}620```bash theme={null}
351#!/bin/bash621#!/bin/bash
352 622
353if [ -n "$CLAUDE_ENV_FILE" ]; then623if [ -n "$CLAUDE_ENV_FILE" ]; then
354 echo 'export NODE_ENV=production' >> "$CLAUDE_ENV_FILE"624 echo 'export NODE_ENV=production' >> "$CLAUDE_ENV_FILE"
355 echo 'export API_KEY=your-api-key' >> "$CLAUDE_ENV_FILE"625 echo 'export DEBUG_LOG=true' >> "$CLAUDE_ENV_FILE"
356 echo 'export PATH="$PATH:./node_modules/.bin"' >> "$CLAUDE_ENV_FILE"626 echo 'export PATH="$PATH:./node_modules/.bin"' >> "$CLAUDE_ENV_FILE"
357fi627fi
358 628
359exit 0629exit 0
360```630```
361 631
362**Example: Persisting all environment changes from the hook**632To capture all environment changes from setup commands, compare the exported variables before and after:
363
364When your setup modifies the environment (e.g., `nvm use`), capture and persist all changes by diffing the environment:
365 633
366```bash theme={null}634```bash theme={null}
367#!/bin/bash635#!/bin/bash
380exit 0648exit 0
381```649```
382 650
383Any variables written to this file will be available in all subsequent bash commands that Claude Code executes during the session.651Any variables written to this file will be available in all subsequent Bash commands that Claude Code executes during the session.
384 652
385<Note>653<Note>
386 `CLAUDE_ENV_FILE` is only available for SessionStart hooks. Other hook types do not have access to this variable.654 `CLAUDE_ENV_FILE` is available for SessionStart hooks. Other hook types do not have access to this variable.
387</Note>655</Note>
388 656
389### SessionEnd657### UserPromptSubmit
390
391Runs when a Claude Code session ends. Useful for cleanup tasks, logging session
392statistics, or saving session state.
393
394The `reason` field in the hook input will be one of:
395
396* `clear` - Session cleared with /clear command
397* `logout` - User logged out
398* `prompt_input_exit` - User exited while prompt input was visible
399* `other` - Other exit reasons
400
401## Hook Input
402
403Hooks receive JSON data via stdin containing session information and
404event-specific data:
405 658
406```typescript theme={null}659Runs when the user submits a prompt, before Claude processes it. This allows you
407{660to add additional context based on the prompt/conversation, validate prompts, or
408 // Common fields661block certain types of prompts.
409 session_id: string
410 transcript_path: string // Path to conversation JSON
411 cwd: string // The current working directory when the hook is invoked
412 permission_mode: string // Current permission mode: "default", "plan", "acceptEdits", or "bypassPermissions"
413
414 // Event-specific fields
415 hook_event_name: string
416 ...
417}
418```
419 662
420### PreToolUse Input663#### UserPromptSubmit input
421 664
422The exact schema for `tool_input` depends on the tool.665In addition to the [common input fields](#common-input-fields), UserPromptSubmit hooks receive the `prompt` field containing the text the user submitted.
423 666
424```json theme={null}667```json theme={null}
425{668{
427 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",670 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
428 "cwd": "/Users/...",671 "cwd": "/Users/...",
429 "permission_mode": "default",672 "permission_mode": "default",
430 "hook_event_name": "PreToolUse",673 "hook_event_name": "UserPromptSubmit",
431 "tool_name": "Write",674 "prompt": "Write a function to calculate the factorial of a number"
432 "tool_input": {
433 "file_path": "/path/to/file.txt",
434 "content": "file content"
435 }
436}675}
437```676```
438 677
439### PostToolUse Input678#### UserPromptSubmit decision control
679
680`UserPromptSubmit` hooks can control whether a user prompt is processed and add context. All [JSON output fields](#json-output) are available.
681
682There are two ways to add context to the conversation on exit code 0:
683
684* **Plain text stdout**: any non-JSON text written to stdout is added as context
685* **JSON with `additionalContext`**: use the JSON format below for more control. The `additionalContext` field is added as context
440 686
441The exact schema for `tool_input` and `tool_response` depends on the tool.687Plain stdout is shown as hook output in the transcript. The `additionalContext` field is added more discretely.
688
689To block a prompt, return a JSON object with `decision` set to `"block"`:
690
691| Field | Description |
692| :------------------ | :----------------------------------------------------------------------------------------------------------------- |
693| `decision` | `"block"` prevents the prompt from being processed and erases it from context. Omit to allow the prompt to proceed |
694| `reason` | Shown to the user when `decision` is `"block"`. Not added to context |
695| `additionalContext` | String added to Claude's context |
442 696
443```json theme={null}697```json theme={null}
444{698{
445 "session_id": "abc123",699 "decision": "block",
446 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",700 "reason": "Explanation for decision",
447 "cwd": "/Users/...",701 "hookSpecificOutput": {
448 "permission_mode": "default",702 "hookEventName": "UserPromptSubmit",
449 "hook_event_name": "PostToolUse",703 "additionalContext": "My additional context here"
450 "tool_name": "Write",704 }
705}
706```
707
708<Note>
709 The JSON format isn't required for simple use cases. To add context, you can print plain text to stdout with exit code 0. Use JSON when you need to
710 block prompts or want more structured control.
711</Note>
712
713### PreToolUse
714
715Runs after Claude creates tool parameters and before processing the tool call. Matches on tool name: `Bash`, `Edit`, `Write`, `Read`, `Glob`, `Grep`, `Task`, `WebFetch`, `WebSearch`, and any [MCP tool names](#match-mcp-tools).
716
717Use [PreToolUse decision control](#pretooluse-decision-control) to allow, deny, or ask for permission to use the tool.
718
719#### PreToolUse input
720
721In addition to the [common input fields](#common-input-fields), PreToolUse hooks receive `tool_name`, `tool_input`, and `tool_use_id`. The `tool_input` fields depend on the tool:
722
723##### Bash
724
725Executes shell commands.
726
727| Field | Type | Example | Description |
728| :------------------ | :------ | :----------------- | :-------------------------------------------- |
729| `command` | string | `"npm test"` | The shell command to execute |
730| `description` | string | `"Run test suite"` | Optional description of what the command does |
731| `timeout` | number | `120000` | Optional timeout in milliseconds |
732| `run_in_background` | boolean | `false` | Whether to run the command in background |
733
734##### Write
735
736Creates or overwrites a file.
737
738| Field | Type | Example | Description |
739| :---------- | :----- | :-------------------- | :--------------------------------- |
740| `file_path` | string | `"/path/to/file.txt"` | Absolute path to the file to write |
741| `content` | string | `"file content"` | Content to write to the file |
742
743##### Edit
744
745Replaces a string in an existing file.
746
747| Field | Type | Example | Description |
748| :------------ | :------ | :-------------------- | :--------------------------------- |
749| `file_path` | string | `"/path/to/file.txt"` | Absolute path to the file to edit |
750| `old_string` | string | `"original text"` | Text to find and replace |
751| `new_string` | string | `"replacement text"` | Replacement text |
752| `replace_all` | boolean | `false` | Whether to replace all occurrences |
753
754##### Read
755
756Reads file contents.
757
758| Field | Type | Example | Description |
759| :---------- | :----- | :-------------------- | :----------------------------------------- |
760| `file_path` | string | `"/path/to/file.txt"` | Absolute path to the file to read |
761| `offset` | number | `10` | Optional line number to start reading from |
762| `limit` | number | `50` | Optional number of lines to read |
763
764##### Glob
765
766Finds files matching a glob pattern.
767
768| Field | Type | Example | Description |
769| :-------- | :----- | :--------------- | :--------------------------------------------------------------------- |
770| `pattern` | string | `"**/*.ts"` | Glob pattern to match files against |
771| `path` | string | `"/path/to/dir"` | Optional directory to search in. Defaults to current working directory |
772
773##### Grep
774
775Searches file contents with regular expressions.
776
777| Field | Type | Example | Description |
778| :------------ | :------ | :--------------- | :------------------------------------------------------------------------------------ |
779| `pattern` | string | `"TODO.*fix"` | Regular expression pattern to search for |
780| `path` | string | `"/path/to/dir"` | Optional file or directory to search in |
781| `glob` | string | `"*.ts"` | Optional glob pattern to filter files |
782| `output_mode` | string | `"content"` | `"content"`, `"files_with_matches"`, or `"count"`. Defaults to `"files_with_matches"` |
783| `-i` | boolean | `true` | Case insensitive search |
784| `multiline` | boolean | `false` | Enable multiline matching |
785
786##### WebFetch
787
788Fetches and processes web content.
789
790| Field | Type | Example | Description |
791| :------- | :----- | :---------------------------- | :----------------------------------- |
792| `url` | string | `"https://example.com/api"` | URL to fetch content from |
793| `prompt` | string | `"Extract the API endpoints"` | Prompt to run on the fetched content |
794
795##### WebSearch
796
797Searches the web.
798
799| Field | Type | Example | Description |
800| :---------------- | :----- | :----------------------------- | :------------------------------------------------ |
801| `query` | string | `"react hooks best practices"` | Search query |
802| `allowed_domains` | array | `["docs.example.com"]` | Optional: only include results from these domains |
803| `blocked_domains` | array | `["spam.example.com"]` | Optional: exclude results from these domains |
804
805##### Task
806
807Spawns a [subagent](/en/sub-agents).
808
809| Field | Type | Example | Description |
810| :-------------- | :----- | :------------------------- | :------------------------------------------- |
811| `prompt` | string | `"Find all API endpoints"` | The task for the agent to perform |
812| `description` | string | `"Find API endpoints"` | Short description of the task |
813| `subagent_type` | string | `"Explore"` | Type of specialized agent to use |
814| `model` | string | `"sonnet"` | Optional model alias to override the default |
815
816#### PreToolUse decision control
817
818`PreToolUse` hooks can control whether a tool call proceeds. Unlike other hooks that use a top-level `decision` field, PreToolUse returns its decision inside a `hookSpecificOutput` object. This gives it richer control: three outcomes (allow, deny, or ask) plus the ability to modify tool input before execution.
819
820| Field | Description |
821| :------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------- |
822| `permissionDecision` | `"allow"` bypasses the permission system, `"deny"` prevents the tool call, `"ask"` prompts the user to confirm |
823| `permissionDecisionReason` | For `"allow"` and `"ask"`, shown to the user but not Claude. For `"deny"`, shown to Claude |
824| `updatedInput` | Modifies the tool's input parameters before execution. Combine with `"allow"` to auto-approve, or `"ask"` to show the modified input to the user |
825| `additionalContext` | String added to Claude's context before the tool executes |
826
827```json theme={null}
828{
829 "hookSpecificOutput": {
830 "hookEventName": "PreToolUse",
831 "permissionDecision": "allow",
832 "permissionDecisionReason": "My reason here",
833 "updatedInput": {
834 "field_to_modify": "new value"
835 },
836 "additionalContext": "Current environment: production. Proceed with caution."
837 }
838}
839```
840
841<Note>
842 PreToolUse previously used top-level `decision` and `reason` fields, but these are deprecated for this event. Use `hookSpecificOutput.permissionDecision` and `hookSpecificOutput.permissionDecisionReason` instead. The deprecated values `"approve"` and `"block"` map to `"allow"` and `"deny"` respectively. Other events like PostToolUse and Stop continue to use top-level `decision` and `reason` as their current format.
843</Note>
844
845### PermissionRequest
846
847Runs when the user is shown a permission dialog.
848Use [PermissionRequest decision control](#permissionrequest-decision-control) to allow or deny on behalf of the user.
849
850Matches on tool name, same values as PreToolUse.
851
852#### PermissionRequest input
853
854PermissionRequest hooks receive `tool_name` and `tool_input` fields like PreToolUse hooks, but without `tool_use_id`. An optional `permission_suggestions` array contains the "always allow" options the user would normally see in the permission dialog. The difference is when the hook fires: PermissionRequest hooks run when a permission dialog is about to be shown to the user, while PreToolUse hooks run before tool execution regardless of permission status.
855
856```json theme={null}
857{
858 "session_id": "abc123",
859 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
860 "cwd": "/Users/...",
861 "permission_mode": "default",
862 "hook_event_name": "PermissionRequest",
863 "tool_name": "Bash",
864 "tool_input": {
865 "command": "rm -rf node_modules",
866 "description": "Remove node_modules directory"
867 },
868 "permission_suggestions": [
869 { "type": "toolAlwaysAllow", "tool": "Bash" }
870 ]
871}
872```
873
874#### PermissionRequest decision control
875
876`PermissionRequest` hooks can allow or deny permission requests. In addition to the [JSON output fields](#json-output) available to all hooks, your hook script can return a `decision` object with these event-specific fields:
877
878| Field | Description |
879| :------------------- | :------------------------------------------------------------------------------------------------------------- |
880| `behavior` | `"allow"` grants the permission, `"deny"` denies it |
881| `updatedInput` | For `"allow"` only: modifies the tool's input parameters before execution |
882| `updatedPermissions` | For `"allow"` only: applies permission rule updates, equivalent to the user selecting an "always allow" option |
883| `message` | For `"deny"` only: tells Claude why the permission was denied |
884| `interrupt` | For `"deny"` only: if `true`, stops Claude |
885
886```json theme={null}
887{
888 "hookSpecificOutput": {
889 "hookEventName": "PermissionRequest",
890 "decision": {
891 "behavior": "allow",
892 "updatedInput": {
893 "command": "npm run lint"
894 }
895 }
896 }
897}
898```
899
900### PostToolUse
901
902Runs immediately after a tool completes successfully.
903
904Matches on tool name, same values as PreToolUse.
905
906#### PostToolUse input
907
908`PostToolUse` hooks fire after a tool has already executed successfully. The input includes both `tool_input`, the arguments sent to the tool, and `tool_response`, the result it returned. The exact schema for both depends on the tool.
909
910```json theme={null}
911{
912 "session_id": "abc123",
913 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
914 "cwd": "/Users/...",
915 "permission_mode": "default",
916 "hook_event_name": "PostToolUse",
917 "tool_name": "Write",
451 "tool_input": {918 "tool_input": {
452 "file_path": "/path/to/file.txt",919 "file_path": "/path/to/file.txt",
453 "content": "file content"920 "content": "file content"
455 "tool_response": {922 "tool_response": {
456 "filePath": "/path/to/file.txt",923 "filePath": "/path/to/file.txt",
457 "success": true924 "success": true
925 },
926 "tool_use_id": "toolu_01ABC123..."
927}
928```
929
930#### PostToolUse decision control
931
932`PostToolUse` hooks can provide feedback to Claude after tool execution. In addition to the [JSON output fields](#json-output) available to all hooks, your hook script can return these event-specific fields:
933
934| Field | Description |
935| :--------------------- | :----------------------------------------------------------------------------------------- |
936| `decision` | `"block"` prompts Claude with the `reason`. Omit to allow the action to proceed |
937| `reason` | Explanation shown to Claude when `decision` is `"block"` |
938| `additionalContext` | Additional context for Claude to consider |
939| `updatedMCPToolOutput` | For [MCP tools](#match-mcp-tools) only: replaces the tool's output with the provided value |
940
941```json theme={null}
942{
943 "decision": "block",
944 "reason": "Explanation for decision",
945 "hookSpecificOutput": {
946 "hookEventName": "PostToolUse",
947 "additionalContext": "Additional information for Claude"
458 }948 }
459}949}
460```950```
461 951
462### Notification Input952### PostToolUseFailure
953
954Runs when a tool execution fails. This event fires for tool calls that throw errors or return failure results. Use this to log failures, send alerts, or provide corrective feedback to Claude.
955
956Matches on tool name, same values as PreToolUse.
957
958#### PostToolUseFailure input
959
960PostToolUseFailure hooks receive the same `tool_name` and `tool_input` fields as PostToolUse, along with error information as top-level fields:
961
962```json theme={null}
963{
964 "session_id": "abc123",
965 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
966 "cwd": "/Users/...",
967 "permission_mode": "default",
968 "hook_event_name": "PostToolUseFailure",
969 "tool_name": "Bash",
970 "tool_input": {
971 "command": "npm test",
972 "description": "Run test suite"
973 },
974 "tool_use_id": "toolu_01ABC123...",
975 "error": "Command exited with non-zero status code 1",
976 "is_interrupt": false
977}
978```
979
980| Field | Description |
981| :------------- | :------------------------------------------------------------------------------ |
982| `error` | String describing what went wrong |
983| `is_interrupt` | Optional boolean indicating whether the failure was caused by user interruption |
984
985#### PostToolUseFailure decision control
986
987`PostToolUseFailure` hooks can provide context to Claude after a tool failure. In addition to the [JSON output fields](#json-output) available to all hooks, your hook script can return these event-specific fields:
988
989| Field | Description |
990| :------------------ | :------------------------------------------------------------ |
991| `additionalContext` | Additional context for Claude to consider alongside the error |
992
993```json theme={null}
994{
995 "hookSpecificOutput": {
996 "hookEventName": "PostToolUseFailure",
997 "additionalContext": "Additional information about the failure for Claude"
998 }
999}
1000```
1001
1002### Notification
1003
1004Runs when Claude Code sends notifications. Matches on notification type: `permission_prompt`, `idle_prompt`, `auth_success`, `elicitation_dialog`. Omit the matcher to run hooks for all notification types.
1005
1006Use separate matchers to run different handlers depending on the notification type. This configuration triggers a permission-specific alert script when Claude needs permission approval and a different notification when Claude has been idle:
1007
1008```json theme={null}
1009{
1010 "hooks": {
1011 "Notification": [
1012 {
1013 "matcher": "permission_prompt",
1014 "hooks": [
1015 {
1016 "type": "command",
1017 "command": "/path/to/permission-alert.sh"
1018 }
1019 ]
1020 },
1021 {
1022 "matcher": "idle_prompt",
1023 "hooks": [
1024 {
1025 "type": "command",
1026 "command": "/path/to/idle-notification.sh"
1027 }
1028 ]
1029 }
1030 ]
1031 }
1032}
1033```
1034
1035#### Notification input
1036
1037In addition to the [common input fields](#common-input-fields), Notification hooks receive `message` with the notification text, an optional `title`, and `notification_type` indicating which type fired.
463 1038
464```json theme={null}1039```json theme={null}
465{1040{
468 "cwd": "/Users/...",1043 "cwd": "/Users/...",
469 "permission_mode": "default",1044 "permission_mode": "default",
470 "hook_event_name": "Notification",1045 "hook_event_name": "Notification",
471 "message": "Task completed successfully"1046 "message": "Claude needs your permission to use Bash",
1047 "title": "Permission needed",
1048 "notification_type": "permission_prompt"
472}1049}
473```1050```
474 1051
475### UserPromptSubmit Input1052Notification hooks cannot block or modify notifications. In addition to the [JSON output fields](#json-output) available to all hooks, you can return `additionalContext` to add context to the conversation:
1053
1054| Field | Description |
1055| :------------------ | :------------------------------- |
1056| `additionalContext` | String added to Claude's context |
1057
1058### SubagentStart
1059
1060Runs when a Claude Code subagent is spawned via the Task tool. Supports matchers to filter by agent type name (built-in agents like `Bash`, `Explore`, `Plan`, or custom agent names from `.claude/agents/`).
1061
1062#### SubagentStart input
1063
1064In addition to the [common input fields](#common-input-fields), SubagentStart hooks receive `agent_id` with the unique identifier for the subagent and `agent_type` with the agent name (built-in agents like `"Bash"`, `"Explore"`, `"Plan"`, or custom agent names).
476 1065
477```json theme={null}1066```json theme={null}
478{1067{
480 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",1069 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
481 "cwd": "/Users/...",1070 "cwd": "/Users/...",
482 "permission_mode": "default",1071 "permission_mode": "default",
483 "hook_event_name": "UserPromptSubmit",1072 "hook_event_name": "SubagentStart",
484 "prompt": "Write a function to calculate the factorial of a number"1073 "agent_id": "agent-abc123",
1074 "agent_type": "Explore"
485}1075}
486```1076```
487 1077
488### Stop and SubagentStop Input1078SubagentStart hooks cannot block subagent creation, but they can inject context into the subagent. In addition to the [JSON output fields](#json-output) available to all hooks, you can return:
489 1079
490`stop_hook_active` is true when Claude Code is already continuing as a result of1080| Field | Description |
491a stop hook. Check this value or process the transcript to prevent Claude Code1081| :------------------ | :------------------------------------- |
492from running indefinitely.1082| `additionalContext` | String added to the subagent's context |
1083
1084```json theme={null}
1085{
1086 "hookSpecificOutput": {
1087 "hookEventName": "SubagentStart",
1088 "additionalContext": "Follow security guidelines for this task"
1089 }
1090}
1091```
1092
1093### SubagentStop
1094
1095Runs when a Claude Code subagent has finished responding. Matches on agent type, same values as SubagentStart.
1096
1097#### SubagentStop input
1098
1099In addition to the [common input fields](#common-input-fields), SubagentStop hooks receive `stop_hook_active`, `agent_id`, `agent_type`, `agent_transcript_path`, and `last_assistant_message`. The `agent_type` field is the value used for matcher filtering. The `transcript_path` is the main session's transcript, while `agent_transcript_path` is the subagent's own transcript stored in a nested `subagents/` folder. The `last_assistant_message` field contains the text content of the subagent's final response, so hooks can access it without parsing the transcript file.
493 1100
494```json theme={null}1101```json theme={null}
495{1102{
496 "session_id": "abc123",1103 "session_id": "abc123",
497 "transcript_path": "~/.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",1104 "transcript_path": "~/.claude/projects/.../abc123.jsonl",
1105 "cwd": "/Users/...",
498 "permission_mode": "default",1106 "permission_mode": "default",
499 "hook_event_name": "Stop",1107 "hook_event_name": "SubagentStop",
500 "stop_hook_active": true1108 "stop_hook_active": false,
1109 "agent_id": "def456",
1110 "agent_type": "Explore",
1111 "agent_transcript_path": "~/.claude/projects/.../abc123/subagents/agent-def456.jsonl",
1112 "last_assistant_message": "Analysis complete. Found 3 potential issues..."
501}1113}
502```1114```
503 1115
504### PreCompact Input1116SubagentStop hooks use the same decision control format as [Stop hooks](#stop-decision-control).
1117
1118### Stop
1119
1120Runs when the main Claude Code agent has finished responding. Does not run if
1121the stoppage occurred due to a user interrupt.
505 1122
506For `manual`, `custom_instructions` comes from what the user passes into1123#### Stop input
507`/compact`. For `auto`, `custom_instructions` is empty.1124
1125In addition to the [common input fields](#common-input-fields), Stop hooks receive `stop_hook_active` and `last_assistant_message`. The `stop_hook_active` field is `true` when Claude Code is already continuing as a result of a stop hook. Check this value or process the transcript to prevent Claude Code from running indefinitely. The `last_assistant_message` field contains the text content of Claude's final response, so hooks can access it without parsing the transcript file.
508 1126
509```json theme={null}1127```json theme={null}
510{1128{
511 "session_id": "abc123",1129 "session_id": "abc123",
512 "transcript_path": "~/.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",1130 "transcript_path": "~/.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
1131 "cwd": "/Users/...",
513 "permission_mode": "default",1132 "permission_mode": "default",
514 "hook_event_name": "PreCompact",1133 "hook_event_name": "Stop",
515 "trigger": "manual",1134 "stop_hook_active": true,
516 "custom_instructions": ""1135 "last_assistant_message": "I've completed the refactoring. Here's a summary..."
517}1136}
518```1137```
519 1138
520### SessionStart Input1139#### Stop decision control
1140
1141`Stop` and `SubagentStop` hooks can control whether Claude continues. In addition to the [JSON output fields](#json-output) available to all hooks, your hook script can return these event-specific fields:
1142
1143| Field | Description |
1144| :--------- | :------------------------------------------------------------------------- |
1145| `decision` | `"block"` prevents Claude from stopping. Omit to allow Claude to stop |
1146| `reason` | Required when `decision` is `"block"`. Tells Claude why it should continue |
1147
1148```json theme={null}
1149{
1150 "decision": "block",
1151 "reason": "Must be provided when Claude is blocked from stopping"
1152}
1153```
1154
1155### TeammateIdle
1156
1157Runs when an [agent team](/en/agent-teams) teammate is about to go idle after finishing its turn. Use this to enforce quality gates before a teammate stops working, such as requiring passing lint checks or verifying that output files exist.
1158
1159When a `TeammateIdle` hook exits with code 2, the teammate receives the stderr message as feedback and continues working instead of going idle. TeammateIdle hooks do not support matchers and fire on every occurrence.
1160
1161#### TeammateIdle input
1162
1163In addition to the [common input fields](#common-input-fields), TeammateIdle hooks receive `teammate_name` and `team_name`.
521 1164
522```json theme={null}1165```json theme={null}
523{1166{
524 "session_id": "abc123",1167 "session_id": "abc123",
525 "transcript_path": "~/.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",1168 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
1169 "cwd": "/Users/...",
526 "permission_mode": "default",1170 "permission_mode": "default",
527 "hook_event_name": "SessionStart",1171 "hook_event_name": "TeammateIdle",
528 "source": "startup"1172 "teammate_name": "researcher",
1173 "team_name": "my-project"
529}1174}
530```1175```
531 1176
532### SessionEnd Input1177| Field | Description |
1178| :-------------- | :-------------------------------------------- |
1179| `teammate_name` | Name of the teammate that is about to go idle |
1180| `team_name` | Name of the team |
1181
1182#### TeammateIdle decision control
1183
1184TeammateIdle hooks use exit codes only, not JSON decision control. This example checks that a build artifact exists before allowing a teammate to go idle:
1185
1186```bash theme={null}
1187#!/bin/bash
1188
1189if [ ! -f "./dist/output.js" ]; then
1190 echo "Build artifact missing. Run the build before stopping." >&2
1191 exit 2
1192fi
1193
1194exit 0
1195```
1196
1197### TaskCompleted
1198
1199Runs when a task is being marked as completed. This fires in two situations: when any agent explicitly marks a task as completed through the TaskUpdate tool, or when an [agent team](/en/agent-teams) teammate finishes its turn with in-progress tasks. Use this to enforce completion criteria like passing tests or lint checks before a task can close.
1200
1201When a `TaskCompleted` hook exits with code 2, the task is not marked as completed and the stderr message is fed back to the model as feedback. TaskCompleted hooks do not support matchers and fire on every occurrence.
1202
1203#### TaskCompleted input
1204
1205In addition to the [common input fields](#common-input-fields), TaskCompleted hooks receive `task_id`, `task_subject`, and optionally `task_description`, `teammate_name`, and `team_name`.
533 1206
534```json theme={null}1207```json theme={null}
535{1208{
536 "session_id": "abc123",1209 "session_id": "abc123",
537 "transcript_path": "~/.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",1210 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
538 "cwd": "/Users/...",1211 "cwd": "/Users/...",
539 "permission_mode": "default",1212 "permission_mode": "default",
540 "hook_event_name": "SessionEnd",1213 "hook_event_name": "TaskCompleted",
541 "reason": "exit"1214 "task_id": "task-001",
1215 "task_subject": "Implement user authentication",
1216 "task_description": "Add login and signup endpoints",
1217 "teammate_name": "implementer",
1218 "team_name": "my-project"
542}1219}
543```1220```
544 1221
545## Hook Output1222| Field | Description |
1223| :----------------- | :------------------------------------------------------ |
1224| `task_id` | Identifier of the task being completed |
1225| `task_subject` | Title of the task |
1226| `task_description` | Detailed description of the task. May be absent |
1227| `teammate_name` | Name of the teammate completing the task. May be absent |
1228| `team_name` | Name of the team. May be absent |
546 1229
547There are two ways for hooks to return output back to Claude Code. The output1230#### TaskCompleted decision control
548communicates whether to block and any feedback that should be shown to Claude
549and the user.
550 1231
551### Simple: Exit Code1232TaskCompleted hooks use exit codes only, not JSON decision control. This example runs tests and blocks task completion if they fail:
552 1233
553Hooks communicate status through exit codes, stdout, and stderr:1234```bash theme={null}
1235#!/bin/bash
1236INPUT=$(cat)
1237TASK_SUBJECT=$(echo "$INPUT" | jq -r '.task_subject')
554 1238
555* **Exit code 0**: Success. `stdout` is shown to the user in transcript mode1239# Run the test suite
556 (CTRL-R), except for `UserPromptSubmit` and `SessionStart`, where stdout is1240if ! npm test 2>&1; then
557 added to the context.1241 echo "Tests not passing. Fix failing tests before completing: $TASK_SUBJECT" >&2
558* **Exit code 2**: Blocking error. `stderr` is fed back to Claude to process1242 exit 2
559 automatically. See per-hook-event behavior below.1243fi
560* **Other exit codes**: Non-blocking error. `stderr` is shown to the user and
561 execution continues.
562 1244
563<Warning>1245exit 0
564 Reminder: Claude Code does not see stdout if the exit code is 0, except for1246```
565 the `UserPromptSubmit` hook where stdout is injected as context.
566</Warning>
567 1247
568#### Exit Code 2 Behavior1248### ConfigChange
569 1249
570| Hook Event | Behavior |1250Runs when a configuration file changes during a session. Use this to audit settings changes, enforce security policies, or block unauthorized modifications to configuration files.
571| ------------------ | ------------------------------------------------------------------ |
572| `PreToolUse` | Blocks the tool call, shows stderr to Claude |
573| `PostToolUse` | Shows stderr to Claude (tool already ran) |
574| `Notification` | N/A, shows stderr to user only |
575| `UserPromptSubmit` | Blocks prompt processing, erases prompt, shows stderr to user only |
576| `Stop` | Blocks stoppage, shows stderr to Claude |
577| `SubagentStop` | Blocks stoppage, shows stderr to Claude subagent |
578| `PreCompact` | N/A, shows stderr to user only |
579| `SessionStart` | N/A, shows stderr to user only |
580| `SessionEnd` | N/A, shows stderr to user only |
581 1251
582### Advanced: JSON Output1252ConfigChange hooks fire for changes to settings files, managed policy settings, and skill files. The `source` field in the input tells you which type of configuration changed, and the optional `file_path` field provides the path to the changed file.
583 1253
584Hooks can return structured JSON in `stdout` for more sophisticated control:1254The matcher filters on the configuration source:
585 1255
586#### Common JSON Fields1256| Matcher | When it fires |
1257| :----------------- | :---------------------------------------- |
1258| `user_settings` | `~/.claude/settings.json` changes |
1259| `project_settings` | `.claude/settings.json` changes |
1260| `local_settings` | `.claude/settings.local.json` changes |
1261| `policy_settings` | Managed policy settings change |
1262| `skills` | A skill file in `.claude/skills/` changes |
587 1263
588All hook types can include these optional fields:1264This example logs all configuration changes for security auditing:
589 1265
590```json theme={null}1266```json theme={null}
591{1267{
592 "continue": true, // Whether Claude should continue after hook execution (default: true)1268 "hooks": {
593 "stopReason": "string", // Message shown when continue is false1269 "ConfigChange": [
1270 {
1271 "hooks": [
1272 {
1273 "type": "command",
1274 "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/audit-config-change.sh"
1275 }
1276 ]
1277 }
1278 ]
1279 }
1280}
1281```
1282
1283#### ConfigChange input
594 1284
595 "suppressOutput": true, // Hide stdout from transcript mode (default: false)1285In addition to the [common input fields](#common-input-fields), ConfigChange hooks receive `source` and optionally `file_path`. The `source` field indicates which configuration type changed, and `file_path` provides the path to the specific file that was modified.
596 "systemMessage": "string" // Optional warning message shown to the user1286
1287```json theme={null}
1288{
1289 "session_id": "abc123",
1290 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
1291 "cwd": "/Users/...",
1292 "permission_mode": "default",
1293 "hook_event_name": "ConfigChange",
1294 "source": "project_settings",
1295 "file_path": "/Users/.../my-project/.claude/settings.json"
597}1296}
598```1297```
599 1298
600If `continue` is false, Claude stops processing after the hooks run.1299#### ConfigChange decision control
601 1300
602* For `PreToolUse`, this is different from `"permissionDecision": "deny"`, which1301ConfigChange hooks can block configuration changes from taking effect. Use exit code 2 or a JSON `decision` to prevent the change. When blocked, the new settings are not applied to the running session.
603 only blocks a specific tool call and provides automatic feedback to Claude.
604* For `PostToolUse`, this is different from `"decision": "block"`, which
605 provides automated feedback to Claude.
606* For `UserPromptSubmit`, this prevents the prompt from being processed.
607* For `Stop` and `SubagentStop`, this takes precedence over any
608 `"decision": "block"` output.
609* In all cases, `"continue" = false` takes precedence over any
610 `"decision": "block"` output.
611 1302
612`stopReason` accompanies `continue` with a reason shown to the user, not shown1303| Field | Description |
613to Claude.1304| :--------- | :--------------------------------------------------------------------------------------- |
1305| `decision` | `"block"` prevents the configuration change from being applied. Omit to allow the change |
1306| `reason` | Explanation shown to the user when `decision` is `"block"` |
614 1307
615#### `PreToolUse` Decision Control1308```json theme={null}
1309{
1310 "decision": "block",
1311 "reason": "Configuration changes to project settings require admin approval"
1312}
1313```
616 1314
617`PreToolUse` hooks can control whether a tool call proceeds.1315`policy_settings` changes cannot be blocked. Hooks still fire for `policy_settings` sources, so you can use them for audit logging, but any blocking decision is ignored. This ensures enterprise-managed settings always take effect.
618 1316
619* `"allow"` bypasses the permission system. `permissionDecisionReason` is shown1317### WorktreeCreate
620 to the user but not to Claude.
621* `"deny"` prevents the tool call from executing. `permissionDecisionReason` is
622 shown to Claude.
623* `"ask"` asks the user to confirm the tool call in the UI.
624 `permissionDecisionReason` is shown to the user but not to Claude.
625 1318
626Additionally, hooks can modify tool inputs before execution using `updatedInput`:1319When you run `claude --worktree` or a [subagent uses `isolation: "worktree"`](/en/sub-agents#choose-the-subagent-scope), Claude Code creates an isolated working copy using `git worktree`. If you configure a WorktreeCreate hook, it replaces the default git behavior, letting you use a different version control system like SVN, Perforce, or Mercurial.
627 1320
628* `updatedInput` allows you to modify the tool's input parameters before the tool executes. This is a `Record<string, unknown>` object containing the fields you want to change or add.1321The hook must print the absolute path to the created worktree directory on stdout. Claude Code uses this path as the working directory for the isolated session.
629* This is most useful with `"permissionDecision": "allow"` to modify and approve tool calls.1322
1323This example creates an SVN working copy and prints the path for Claude Code to use. Replace the repository URL with your own:
630 1324
631```json theme={null}1325```json theme={null}
632{1326{
633 "hookSpecificOutput": {1327 "hooks": {
634 "hookEventName": "PreToolUse",1328 "WorktreeCreate": [
635 "permissionDecision": "allow"1329 {
636 "permissionDecisionReason": "My reason here",1330 "hooks": [
637 "updatedInput": {1331 {
638 "field_to_modify": "new value"1332 "type": "command",
1333 "command": "bash -c 'NAME=$(jq -r .name); DIR=\"$HOME/.claude/worktrees/$NAME\"; svn checkout https://svn.example.com/repo/trunk \"$DIR\" >&2 && echo \"$DIR\"'"
1334 }
1335 ]
639 }1336 }
1337 ]
640 }1338 }
641}1339}
642```1340```
643 1341
644<Note>1342The hook reads the worktree `name` from the JSON input on stdin, checks out a fresh copy into a new directory, and prints the directory path. The `echo` on the last line is what Claude Code reads as the worktree path. Redirect any other output to stderr so it doesn't interfere with the path.
645 The `decision` and `reason` fields are deprecated for PreToolUse hooks.
646 Use `hookSpecificOutput.permissionDecision` and
647 `hookSpecificOutput.permissionDecisionReason` instead. The deprecated fields
648 `"approve"` and `"block"` map to `"allow"` and `"deny"` respectively.
649</Note>
650 1343
651#### `PostToolUse` Decision Control1344#### WorktreeCreate input
652 1345
653`PostToolUse` hooks can provide feedback to Claude after tool execution.1346In addition to the [common input fields](#common-input-fields), WorktreeCreate hooks receive the `name` field. This is a slug identifier for the new worktree, either specified by the user or auto-generated (for example, `bold-oak-a3f2`).
654 1347
655* `"block"` automatically prompts Claude with `reason`.1348```json theme={null}
656* `undefined` does nothing. `reason` is ignored.1349{
657* `"hookSpecificOutput.additionalContext"` adds context for Claude to consider.1350 "session_id": "abc123",
1351 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
1352 "cwd": "/Users/...",
1353 "hook_event_name": "WorktreeCreate",
1354 "name": "feature-auth"
1355}
1356```
1357
1358#### WorktreeCreate output
1359
1360The hook must print the absolute path to the created worktree directory on stdout. If the hook fails or produces no output, worktree creation fails with an error.
1361
1362WorktreeCreate hooks do not use the standard allow/block decision model. Instead, the hook's success or failure determines the outcome. Only `type: "command"` hooks are supported.
1363
1364### WorktreeRemove
1365
1366The cleanup counterpart to [WorktreeCreate](#worktreecreate). This hook fires when a worktree is being removed, either when you exit a `--worktree` session and choose to remove it, or when a subagent with `isolation: "worktree"` finishes. For git-based worktrees, Claude handles cleanup automatically with `git worktree remove`. If you configured a WorktreeCreate hook for a non-git version control system, pair it with a WorktreeRemove hook to handle cleanup. Without one, the worktree directory is left on disk.
1367
1368Claude Code passes the path that WorktreeCreate printed on stdout as `worktree_path` in the hook input. This example reads that path and removes the directory:
658 1369
659```json theme={null}1370```json theme={null}
660{1371{
661 "decision": "block" | undefined,1372 "hooks": {
662 "reason": "Explanation for decision",1373 "WorktreeRemove": [
663 "hookSpecificOutput": {1374 {
664 "hookEventName": "PostToolUse",1375 "hooks": [
665 "additionalContext": "Additional information for Claude"1376 {
1377 "type": "command",
1378 "command": "bash -c 'jq -r .worktree_path | xargs rm -rf'"
1379 }
1380 ]
1381 }
1382 ]
666 }1383 }
667}1384}
668```1385```
669 1386
670#### `UserPromptSubmit` Decision Control1387#### WorktreeRemove input
1388
1389In addition to the [common input fields](#common-input-fields), WorktreeRemove hooks receive the `worktree_path` field, which is the absolute path to the worktree being removed.
1390
1391```json theme={null}
1392{
1393 "session_id": "abc123",
1394 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
1395 "cwd": "/Users/...",
1396 "hook_event_name": "WorktreeRemove",
1397 "worktree_path": "/Users/.../my-project/.claude/worktrees/feature-auth"
1398}
1399```
1400
1401WorktreeRemove hooks have no decision control. They cannot block worktree removal but can perform cleanup tasks like removing version control state or archiving changes. Hook failures are logged in debug mode only. Only `type: "command"` hooks are supported.
671 1402
672`UserPromptSubmit` hooks can control whether a user prompt is processed.1403### PreCompact
673 1404
674* `"block"` prevents the prompt from being processed. The submitted prompt is1405Runs before Claude Code is about to run a compact operation.
675 erased from context. `"reason"` is shown to the user but not added to context.1406
676* `undefined` allows the prompt to proceed normally. `"reason"` is ignored.1407The matcher value indicates whether compaction was triggered manually or automatically:
677* `"hookSpecificOutput.additionalContext"` adds the string to the context if not1408
678 blocked.1409| Matcher | When it fires |
1410| :------- | :------------------------------------------- |
1411| `manual` | `/compact` |
1412| `auto` | Auto-compact when the context window is full |
1413
1414#### PreCompact input
1415
1416In addition to the [common input fields](#common-input-fields), PreCompact hooks receive `trigger` and `custom_instructions`. For `manual`, `custom_instructions` contains what the user passes into `/compact`. For `auto`, `custom_instructions` is empty.
679 1417
680```json theme={null}1418```json theme={null}
681{1419{
682 "decision": "block" | undefined,1420 "session_id": "abc123",
683 "reason": "Explanation for decision",1421 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
684 "hookSpecificOutput": {1422 "cwd": "/Users/...",
685 "hookEventName": "UserPromptSubmit",1423 "permission_mode": "default",
686 "additionalContext": "My additional context here"1424 "hook_event_name": "PreCompact",
687 }1425 "trigger": "manual",
1426 "custom_instructions": ""
688}1427}
689```1428```
690 1429
691#### `Stop`/`SubagentStop` Decision Control1430### SessionEnd
1431
1432Runs when a Claude Code session ends. Useful for cleanup tasks, logging session
1433statistics, or saving session state. Supports matchers to filter by exit reason.
1434
1435The `reason` field in the hook input indicates why the session ended:
1436
1437| Reason | Description |
1438| :---------------------------- | :----------------------------------------- |
1439| `clear` | Session cleared with `/clear` command |
1440| `logout` | User logged out |
1441| `prompt_input_exit` | User exited while prompt input was visible |
1442| `bypass_permissions_disabled` | Bypass permissions mode was disabled |
1443| `other` | Other exit reasons |
692 1444
693`Stop` and `SubagentStop` hooks can control whether Claude must continue.1445#### SessionEnd input
694 1446
695* `"block"` prevents Claude from stopping. You must populate `reason` for Claude1447In addition to the [common input fields](#common-input-fields), SessionEnd hooks receive a `reason` field indicating why the session ended. See the [reason table](#sessionend) above for all values.
696 to know how to proceed.
697* `undefined` allows Claude to stop. `reason` is ignored.
698 1448
699```json theme={null}1449```json theme={null}
700{1450{
701 "decision": "block" | undefined,1451 "session_id": "abc123",
702 "reason": "Must be provided when Claude is blocked from stopping"1452 "transcript_path": "/Users/.../.claude/projects/.../00893aaf-19fa-41d2-8238-13269b9b3ca0.jsonl",
1453 "cwd": "/Users/...",
1454 "permission_mode": "default",
1455 "hook_event_name": "SessionEnd",
1456 "reason": "other"
703}1457}
704```1458```
705 1459
706#### `SessionStart` Decision Control1460SessionEnd hooks have no decision control. They cannot block session termination but can perform cleanup tasks.
1461
1462## Prompt-based hooks
1463
1464In addition to Bash command hooks (`type: "command"`), Claude Code supports prompt-based hooks (`type: "prompt"`) that use an LLM to evaluate whether to allow or block an action, and agent hooks (`type: "agent"`) that spawn an agentic verifier with tool access. Not all events support every hook type.
1465
1466Events that support all three hook types (`command`, `prompt`, and `agent`):
1467
1468* `PermissionRequest`
1469* `PostToolUse`
1470* `PostToolUseFailure`
1471* `PreToolUse`
1472* `Stop`
1473* `SubagentStop`
1474* `TaskCompleted`
1475* `UserPromptSubmit`
1476
1477Events that only support `type: "command"` hooks:
1478
1479* `ConfigChange`
1480* `Notification`
1481* `PreCompact`
1482* `SessionEnd`
1483* `SessionStart`
1484* `SubagentStart`
1485* `TeammateIdle`
1486* `WorktreeCreate`
1487* `WorktreeRemove`
1488
1489### How prompt-based hooks work
1490
1491Instead of executing a Bash command, prompt-based hooks:
707 1492
708`SessionStart` hooks allow you to load in context at the start of a session.14931. Send the hook input and your prompt to a Claude model, Haiku by default
14942. The LLM responds with structured JSON containing a decision
14953. Claude Code processes the decision automatically
1496
1497### Prompt hook configuration
1498
1499Set `type` to `"prompt"` and provide a `prompt` string instead of a `command`. Use the `$ARGUMENTS` placeholder to inject the hook's JSON input data into your prompt text. Claude Code sends the combined prompt and input to a fast Claude model, which returns a JSON decision.
709 1500
710* `"hookSpecificOutput.additionalContext"` adds the string to the context.1501This `Stop` hook asks the LLM to evaluate whether all tasks are complete before allowing Claude to finish:
711* Multiple hooks' `additionalContext` values are concatenated.
712 1502
713```json theme={null}1503```json theme={null}
714{1504{
715 "hookSpecificOutput": {1505 "hooks": {
716 "hookEventName": "SessionStart",1506 "Stop": [
717 "additionalContext": "My additional context here"1507 {
1508 "hooks": [
1509 {
1510 "type": "prompt",
1511 "prompt": "Evaluate if Claude should stop: $ARGUMENTS. Check if all tasks are complete."
1512 }
1513 ]
1514 }
1515 ]
718 }1516 }
719}1517}
720```1518```
721 1519
722#### `SessionEnd` Decision Control1520| Field | Required | Description |
723 1521| :-------- | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
724`SessionEnd` hooks run when a session ends. They cannot block session termination1522| `type` | yes | Must be `"prompt"` |
725but can perform cleanup tasks.1523| `prompt` | yes | The prompt text to send to the LLM. Use `$ARGUMENTS` as a placeholder for the hook input JSON. If `$ARGUMENTS` is not present, input JSON is appended to the prompt |
726 1524| `model` | no | Model to use for evaluation. Defaults to a fast model |
727#### Exit Code Example: Bash Command Validation1525| `timeout` | no | Timeout in seconds. Default: 30 |
728 1526
729```python theme={null}1527### Response schema
730#!/usr/bin/env python31528
731import json1529The LLM must respond with JSON containing:
732import re1530
733import sys1531```json theme={null}
734 1532{
735# Define validation rules as a list of (regex pattern, message) tuples1533 "ok": true | false,
736VALIDATION_RULES = [1534 "reason": "Explanation for the decision"
737 (1535}
738 r"\bgrep\b(?!.*\|)",
739 "Use 'rg' (ripgrep) instead of 'grep' for better performance and features",
740 ),
741 (
742 r"\bfind\s+\S+\s+-name\b",
743 "Use 'rg --files | rg pattern' or 'rg --files -g pattern' instead of 'find -name' for better performance",
744 ),
745]
746
747
748def validate_command(command: str) -> list[str]:
749 issues = []
750 for pattern, message in VALIDATION_RULES:
751 if re.search(pattern, command):
752 issues.append(message)
753 return issues
754
755
756try:
757 input_data = json.load(sys.stdin)
758except json.JSONDecodeError as e:
759 print(f"Error: Invalid JSON input: {e}", file=sys.stderr)
760 sys.exit(1)
761
762tool_name = input_data.get("tool_name", "")
763tool_input = input_data.get("tool_input", {})
764command = tool_input.get("command", "")
765
766if tool_name != "Bash" or not command:
767 sys.exit(1)
768
769# Validate the command
770issues = validate_command(command)
771
772if issues:
773 for message in issues:
774 print(f"• {message}", file=sys.stderr)
775 # Exit code 2 blocks tool call and shows stderr to Claude
776 sys.exit(2)
777```1536```
778 1537
779#### JSON Output Example: UserPromptSubmit to Add Context and Validation1538| Field | Description |
1539| :------- | :--------------------------------------------------------- |
1540| `ok` | `true` allows the action, `false` prevents it |
1541| `reason` | Required when `ok` is `false`. Explanation shown to Claude |
780 1542
781<Note>1543### Example: Multi-criteria Stop hook
782 For `UserPromptSubmit` hooks, you can inject context using either method:
783 1544
784 * Exit code 0 with stdout: Claude sees the context (special case for `UserPromptSubmit`)1545This `Stop` hook uses a detailed prompt to check three conditions before allowing Claude to stop. If `"ok"` is `false`, Claude continues working with the provided reason as its next instruction. `SubagentStop` hooks use the same format to evaluate whether a [subagent](/en/sub-agents) should stop:
785 * JSON output: Provides more control over the behavior
786</Note>
787 1546
788```python theme={null}1547```json theme={null}
789#!/usr/bin/env python31548{
790import json1549 "hooks": {
791import sys1550 "Stop": [
792import re1551 {
793import datetime1552 "hooks": [
794 1553 {
795# Load input from stdin1554 "type": "prompt",
796try:1555 "prompt": "You are evaluating whether Claude should stop working. Context: $ARGUMENTS\n\nAnalyze the conversation and determine if:\n1. All user-requested tasks are complete\n2. Any errors need to be addressed\n3. Follow-up work is needed\n\nRespond with JSON: {\"ok\": true} to allow stopping, or {\"ok\": false, \"reason\": \"your explanation\"} to continue working.",
797 input_data = json.load(sys.stdin)1556 "timeout": 30
798except json.JSONDecodeError as e:1557 }
799 print(f"Error: Invalid JSON input: {e}", file=sys.stderr)1558 ]
800 sys.exit(1)
801
802prompt = input_data.get("prompt", "")
803
804# Check for sensitive patterns
805sensitive_patterns = [
806 (r"(?i)\b(password|secret|key|token)\s*[:=]", "Prompt contains potential secrets"),
807]
808
809for pattern, message in sensitive_patterns:
810 if re.search(pattern, prompt):
811 # Use JSON output to block with a specific reason
812 output = {
813 "decision": "block",
814 "reason": f"Security policy violation: {message}. Please rephrase your request without sensitive information."
815 }1559 }
816 print(json.dumps(output))1560 ]
817 sys.exit(0)1561 }
1562}
1563```
818 1564
819# Add current time to context1565## Agent-based hooks
820context = f"Current time: {datetime.datetime.now()}"
821print(context)
822 1566
823"""1567Agent-based hooks (`type: "agent"`) are like prompt-based hooks but with multi-turn tool access. Instead of a single LLM call, an agent hook spawns a subagent that can read files, search code, and inspect the codebase to verify conditions. Agent hooks support the same events as prompt-based hooks.
824The following is also equivalent:
825print(json.dumps({
826 "hookSpecificOutput": {
827 "hookEventName": "UserPromptSubmit",
828 "additionalContext": context,
829 },
830}))
831"""
832 1568
833# Allow the prompt to proceed with the additional context1569### How agent hooks work
834sys.exit(0)
835```
836 1570
837#### JSON Output Example: PreToolUse with Approval1571When an agent hook fires:
838
839```python theme={null}
840#!/usr/bin/env python3
841import json
842import sys
843
844# Load input from stdin
845try:
846 input_data = json.load(sys.stdin)
847except json.JSONDecodeError as e:
848 print(f"Error: Invalid JSON input: {e}", file=sys.stderr)
849 sys.exit(1)
850
851tool_name = input_data.get("tool_name", "")
852tool_input = input_data.get("tool_input", {})
853
854# Example: Auto-approve file reads for documentation files
855if tool_name == "Read":
856 file_path = tool_input.get("file_path", "")
857 if file_path.endswith((".md", ".mdx", ".txt", ".json")):
858 # Use JSON output to auto-approve the tool call
859 output = {
860 "decision": "approve",
861 "reason": "Documentation file auto-approved",
862 "suppressOutput": True # Don't show in transcript mode
863 }
864 print(json.dumps(output))
865 sys.exit(0)
866
867# For other cases, let the normal permission flow proceed
868sys.exit(0)
869```
870 1572
871## Working with MCP Tools15731. Claude Code spawns a subagent with your prompt and the hook's JSON input
15742. The subagent can use tools like Read, Grep, and Glob to investigate
15753. After up to 50 turns, the subagent returns a structured `{ "ok": true/false }` decision
15764. Claude Code processes the decision the same way as a prompt hook
872 1577
873Claude Code hooks work seamlessly with1578Agent hooks are useful when verification requires inspecting actual files or test output, not just evaluating the hook input data alone.
874[Model Context Protocol (MCP) tools](/en/mcp). When MCP servers
875provide tools, they appear with a special naming pattern that you can match in
876your hooks.
877 1579
878### MCP Tool Naming1580### Agent hook configuration
879 1581
880MCP tools follow the pattern `mcp__<server>__<tool>`, for example:1582Set `type` to `"agent"` and provide a `prompt` string. The configuration fields are the same as [prompt hooks](#prompt-hook-configuration), with a longer default timeout:
881 1583
882* `mcp__memory__create_entities` - Memory server's create entities tool1584| Field | Required | Description |
883* `mcp__filesystem__read_file` - Filesystem server's read file tool1585| :-------- | :------- | :------------------------------------------------------------------------------------------ |
884* `mcp__github__search_repositories` - GitHub server's search tool1586| `type` | yes | Must be `"agent"` |
1587| `prompt` | yes | Prompt describing what to verify. Use `$ARGUMENTS` as a placeholder for the hook input JSON |
1588| `model` | no | Model to use. Defaults to a fast model |
1589| `timeout` | no | Timeout in seconds. Default: 60 |
885 1590
886### Configuring Hooks for MCP Tools1591The response schema is the same as prompt hooks: `{ "ok": true }` to allow or `{ "ok": false, "reason": "..." }` to block.
887 1592
888You can target specific MCP tools or entire MCP servers:1593This `Stop` hook verifies that all unit tests pass before allowing Claude to finish:
889 1594
890```json theme={null}1595```json theme={null}
891{1596{
892 "hooks": {1597 "hooks": {
893 "PreToolUse": [1598 "Stop": [
894 {1599 {
895 "matcher": "mcp__memory__.*",
896 "hooks": [1600 "hooks": [
897 {1601 {
898 "type": "command",1602 "type": "agent",
899 "command": "echo 'Memory operation initiated' >> ~/mcp-operations.log"1603 "prompt": "Verify that all unit tests pass. Run the test suite and check the results. $ARGUMENTS",
1604 "timeout": 120
900 }1605 }
901 ]1606 ]
902 },1607 }
1608 ]
1609 }
1610}
1611```
1612
1613## Run hooks in the background
1614
1615By default, hooks block Claude's execution until they complete. For long-running tasks like deployments, test suites, or external API calls, set `"async": true` to run the hook in the background while Claude continues working. Async hooks cannot block or control Claude's behavior: response fields like `decision`, `permissionDecision`, and `continue` have no effect, because the action they would have controlled has already completed.
1616
1617### Configure an async hook
1618
1619Add `"async": true` to a command hook's configuration to run it in the background without blocking Claude. This field is only available on `type: "command"` hooks.
1620
1621This hook runs a test script after every `Write` tool call. Claude continues working immediately while `run-tests.sh` executes for up to 120 seconds. When the script finishes, its output is delivered on the next conversation turn:
1622
1623```json theme={null}
1624{
1625 "hooks": {
1626 "PostToolUse": [
903 {1627 {
904 "matcher": "mcp__.*__write.*",1628 "matcher": "Write",
905 "hooks": [1629 "hooks": [
906 {1630 {
907 "type": "command",1631 "type": "command",
908 "command": "/home/user/scripts/validate-mcp-write.py"1632 "command": "/path/to/run-tests.sh",
1633 "async": true,
1634 "timeout": 120
909 }1635 }
910 ]1636 ]
911 }1637 }
914}1640}
915```1641```
916 1642
917## Examples1643The `timeout` field sets the maximum time in seconds for the background process. If not specified, async hooks use the same 10-minute default as sync hooks.
918
919<Tip>
920 For practical examples including code formatting, notifications, and file protection, see [More Examples](/en/hooks-guide#more-examples) in the get started guide.
921</Tip>
922 1644
923## Security Considerations1645### How async hooks execute
924
925### Disclaimer
926 1646
927**USE AT YOUR OWN RISK**: Claude Code hooks execute arbitrary shell commands on1647When an async hook fires, Claude Code starts the hook process and immediately continues without waiting for it to finish. The hook receives the same JSON input via stdin as a synchronous hook.
928your system automatically. By using hooks, you acknowledge that:
929 1648
930* You are solely responsible for the commands you configure1649After the background process exits, if the hook produced a JSON response with a `systemMessage` or `additionalContext` field, that content is delivered to Claude as context on the next conversation turn.
931* Hooks can modify, delete, or access any files your user account can access
932* Malicious or poorly written hooks can cause data loss or system damage
933* Anthropic provides no warranty and assumes no liability for any damages
934 resulting from hook usage
935* You should thoroughly test hooks in a safe environment before production use
936 1650
937Always review and understand any hook commands before adding them to your1651### Example: run tests after file changes
938configuration.
939 1652
940### Security Best Practices1653This hook starts a test suite in the background whenever Claude writes a file, then reports the results back to Claude when the tests finish. Save this script to `.claude/hooks/run-tests-async.sh` in your project and make it executable with `chmod +x`:
941 1654
942Here are some key practices for writing more secure hooks:1655```bash theme={null}
1656#!/bin/bash
1657# run-tests-async.sh
943 1658
9441. **Validate and sanitize inputs** - Never trust input data blindly1659# Read hook input from stdin
9452. **Always quote shell variables** - Use `"$VAR"` not `$VAR`1660INPUT=$(cat)
9463. **Block path traversal** - Check for `..` in file paths1661FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
9474. **Use absolute paths** - Specify full paths for scripts (use
948 "\$CLAUDE\_PROJECT\_DIR" for the project path)
9495. **Skip sensitive files** - Avoid `.env`, `.git/`, keys, etc.
950 1662
951### Configuration Safety1663# Only run tests for source files
1664if [[ "$FILE_PATH" != *.ts && "$FILE_PATH" != *.js ]]; then
1665 exit 0
1666fi
952 1667
953Direct edits to hooks in settings files don't take effect immediately. Claude1668# Run tests and report results via systemMessage
954Code:1669RESULT=$(npm test 2>&1)
1670EXIT_CODE=$?
955 1671
9561. Captures a snapshot of hooks at startup1672if [ $EXIT_CODE -eq 0 ]; then
9572. Uses this snapshot throughout the session1673 echo "{\"systemMessage\": \"Tests passed after editing $FILE_PATH\"}"
9583. Warns if hooks are modified externally1674else
9594. Requires review in `/hooks` menu for changes to apply1675 echo "{\"systemMessage\": \"Tests failed after editing $FILE_PATH: $RESULT\"}"
1676fi
1677```
960 1678
961This prevents malicious hook modifications from affecting your current session.1679Then add this configuration to `.claude/settings.json` in your project root. The `async: true` flag lets Claude keep working while tests run:
962 1680
963## Hook Execution Details1681```json theme={null}
1682{
1683 "hooks": {
1684 "PostToolUse": [
1685 {
1686 "matcher": "Write|Edit",
1687 "hooks": [
1688 {
1689 "type": "command",
1690 "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/run-tests-async.sh",
1691 "async": true,
1692 "timeout": 300
1693 }
1694 ]
1695 }
1696 ]
1697 }
1698}
1699```
964 1700
965* **Timeout**: 60-second execution limit by default, configurable per command.1701### Limitations
966 * A timeout for an individual command does not affect the other commands.
967* **Parallelization**: All matching hooks run in parallel
968* **Deduplication**: Multiple identical hook commands are deduplicated automatically
969* **Environment**: Runs in current directory with Claude Code's environment
970 * The `CLAUDE_PROJECT_DIR` environment variable is available and contains the
971 absolute path to the project root directory (where Claude Code was started)
972 * The `CLAUDE_CODE_REMOTE` environment variable indicates whether the hook is running in a remote (web) environment (`"true"`) or local CLI environment (not set or empty). Use this to run different logic based on execution context.
973* **Input**: JSON via stdin
974* **Output**:
975 * PreToolUse/PostToolUse/Stop/SubagentStop: Progress shown in transcript (Ctrl-R)
976 * Notification/SessionEnd: Logged to debug only (`--debug`)
977 * UserPromptSubmit/SessionStart: stdout added as context for Claude
978 1702
979## Debugging1703Async hooks have several constraints compared to synchronous hooks:
980 1704
981### Basic Troubleshooting1705* Only `type: "command"` hooks support `async`. Prompt-based hooks cannot run asynchronously.
1706* Async hooks cannot block tool calls or return decisions. By the time the hook completes, the triggering action has already proceeded.
1707* Hook output is delivered on the next conversation turn. If the session is idle, the response waits until the next user interaction.
1708* Each execution creates a separate background process. There is no deduplication across multiple firings of the same async hook.
982 1709
983If your hooks aren't working:1710## Security considerations
984 1711
9851. **Check configuration** - Run `/hooks` to see if your hook is registered1712### Disclaimer
9862. **Verify syntax** - Ensure your JSON settings are valid
9873. **Test commands** - Run hook commands manually first
9884. **Check permissions** - Make sure scripts are executable
9895. **Review logs** - Use `claude --debug` to see hook execution details
990 1713
991Common issues:1714Hooks run with your system user's full permissions.
992 1715
993* **Quotes not escaped** - Use `\"` inside JSON strings1716<Warning>
994* **Wrong matcher** - Check tool names match exactly (case-sensitive)1717 Hooks execute shell commands with your full user permissions. They can modify, delete, or access any files your user account can access. Review and test all hook commands before adding them to your configuration.
995* **Command not found** - Use full paths for scripts1718</Warning>
996 1719
997### Advanced Debugging1720### Security best practices
998 1721
999For complex hook issues:1722Keep these practices in mind when writing hooks:
1000 1723
10011. **Inspect hook execution** - Use `claude --debug` to see detailed hook1724* **Validate and sanitize inputs**: never trust input data blindly
1002 execution1725* **Always quote shell variables**: use `"$VAR"` not `$VAR`
10032. **Validate JSON schemas** - Test hook input/output with external tools1726* **Block path traversal**: check for `..` in file paths
10043. **Check environment variables** - Verify Claude Code's environment is correct1727* **Use absolute paths**: specify full paths for scripts, using `"$CLAUDE_PROJECT_DIR"` for the project root
10054. **Test edge cases** - Try hooks with unusual file paths or inputs1728* **Skip sensitive files**: avoid `.env`, `.git/`, keys, etc.
10065. **Monitor system resources** - Check for resource exhaustion during hook
1007 execution
10086. **Use structured logging** - Implement logging in your hook scripts
1009 1729
1010### Debug Output Example1730## Debug hooks
1011 1731
1012Use `claude --debug` to see hook execution details:1732Run `claude --debug` to see hook execution details, including which hooks matched, their exit codes, and output. Toggle verbose mode with `Ctrl+O` to see hook progress in the transcript.
1013 1733
1014```1734```
1015[DEBUG] Executing hooks for PostToolUse:Write1735[DEBUG] Executing hooks for PostToolUse:Write
1017[DEBUG] Found 1 hook matchers in settings1737[DEBUG] Found 1 hook matchers in settings
1018[DEBUG] Matched 1 hooks for query "Write"1738[DEBUG] Matched 1 hooks for query "Write"
1019[DEBUG] Found 1 hook commands to execute1739[DEBUG] Found 1 hook commands to execute
1020[DEBUG] Executing hook command: <Your command> with timeout 60000ms1740[DEBUG] Executing hook command: <Your command> with timeout 600000ms
1021[DEBUG] Hook command completed with status 0: <Your stdout>1741[DEBUG] Hook command completed with status 0: <Your stdout>
1022```1742```
1023 1743
1024Progress messages appear in transcript mode (Ctrl-R) showing:1744For troubleshooting common issues like hooks not firing, infinite Stop hook loops, or configuration errors, see [Limitations and troubleshooting](/en/hooks-guide#limitations-and-troubleshooting) in the guide.
1025
1026* Which hook is running
1027* Command being executed
1028* Success/failure status
1029* Output or error messages
