A reference for Claude Code hooks, which are automated actions that run when events such as tool use, prompts, session changes, or agent handoffs occur. It lists hook types, common uses, and configuration locations.

Use it to run validation before tools execute, inspect results afterward, preprocess prompts, handle permissions, log sessions, or configure Claude Code automation.

It helps automate checks and responses around coding-agent activity and troubleshoot hooks that do not run as expected.

plugin:hook — Skill for Claude Code by bendrucker/claude

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

agentmods

npx agentmods add skills/bendrucker/claude/hook

Made for: Claude Code.

Or install plugin, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/hook/github.svg)](https://agentmods.dev/skills/bendrucker/claude/hook)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/hook"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/hook/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bendrucker/claude/hook"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/hook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,614 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.01614
Opus 5.5	$0.00033	$0.00646
Sonnet 5.5	$0.00016	$0.00323
Haiku 4.5	$0.00008	$0.00161

Measured 1mo ago against content hash 52d55f417e9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

plugin:hook scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `~/.claude/settings.json` - User-level (global)

plugins/plugin/skills/hook/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Hooks

Reference for creating and configuring Claude Code hooks. When uncertain about syntax or features, use the Agent tool with subagent_type='claude-code-guide' to consult official docs.

Hook Types

Type	Trigger	Use Cases
PreToolUse	Before tool execution	Validate inputs, block operations, modify parameters
PostToolUse	After tool completes	Check results, run linters, provide feedback
UserPromptSubmit	When user sends message	Pre-process input, add context
PermissionRequest	Permission dialog appears	Return a decision, notify a remote approver
Stop	Agent finishes a turn	Cleanup, save state
StopFailure	Agent stops on failure	Report the failure
SubagentStart / SubagentStop	Subagent spawns / completes	Process results
SessionStart / SessionEnd	Session begins / ends	Inject context, export state
PreCompact / PostCompact	Around context compaction	Save important state
Notification	System notification	Log events
TeammateIdle	Teammate about to go idle	Hand off work

Configuration Files

~/.claude/settings.json - User-level (global)
.claude/settings.json - Project-level
.claude/settings.local.json - Local (not committed)
Plugin hooks: plugins/<name>/hooks/hooks.json

Hook Structure

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "bun ./hooks/ox"
          }
        ]
      }
    ]
  }
}

Matcher Patterns

Simple: "Write", "Edit"
Multiple: "Edit|Write|MultiEdit"
With args: "Bash(npm:*)", "Bash(osascript:*)|Bash(open:*)"
MCP tools: "mcp__linear__create_issue"
Plugin MCP tools: "mcp__plugin_<plugin>_<namespace>__<tool>"
Claude AI MCP tools: "mcp__claude_ai_<DisplayName>__<tool>"
All three patterns: "mcp__linear__create_issue|mcp__plugin_linear_linear__create_issue|mcp__claude_ai_Linear__save_issue"

Read the full file on GitHub · 164 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/debugging.md 2.2 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · -2 tokens per session 52d55f417e9f
2mo ago Changed · +19 lines 1710af10cbea
2mo ago First seen · 145 lines · 84 tokens per session scan B c2c5bf56056c

Subscribe to this mod's changes

plugin:hook is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,614 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code claude-code-plugin

plugin:hook next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plugin:hookbendrucker/claude	Skill	18	today	MIT	B	82	Claude Code
reviewSethGammon/Citadel	Skill	928	4d ago	MIT	A	17	Claude Code
system-upgradealivecontext/alive	Skill	132	yesterday	MIT	A	55	Claude Code
wenlan-handoffwenlan-app/wenlan	Skill	94	today	Apache-2.0	A	43	Claude Code, Codex
extract-resumesuxrobGM/jobpilot	Skill	111	today	MIT	A	32	Claude Code
pr-reviewnitinjain999/platform-skills	Skill	71	yesterday	Apache-2.0	A	81	Claude Code
read-literaturefirecrawl/firecrawl-claude-plugin	Skill	258	3d ago	MIT	A	101	Claude Code

plugin:hook