hook-creator

A guide for creating Claude Code hooks, shell commands that run automatically at specified assistant or tool events.

In plain words
What is it for?
Use it to configure formatting, logging, notifications, file protection, permissions, or actions before and after tools run.
Why use it?
It helps automate checks and actions without relying on someone to run them manually.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/greatsumini/cc-system/hook-creator
Any agent
npx skills add greatSumini/cc-system --skill hook-creator
Clone the repo
git clone --depth 1 https://github.com/greatSumini/cc-system

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 660 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00083 $0.00660
Opus 5 $0.00042 $0.00330
Sonnet 5 $0.00017 $0.00132
Haiku 4.5 $0.00008 $0.00066

Measured yesterday against content hash d046588831ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

hook-creator 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 yesterday.

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.

5. **Choose storage location** - User settings (`~/.claude/settings.json`) or project (`.claude/settings.json`)
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/hook-creator/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hook Creator

Create Claude Code hooks that execute shell commands at specific lifecycle events.

Hook Creation Workflow

  1. Identify the use case - Determine what the hook should accomplish
  2. Select the appropriate event - Choose from available hook events (see references/hook-events.md)
  3. Design the hook command - Write shell command that processes JSON input from stdin
  4. Configure the matcher - Set tool/event filter (use * for all, or specific tool names like Bash, Edit|Write)
  5. Choose storage location - User settings (~/.claude/settings.json) or project (.claude/settings.json)
  6. Test the hook - Verify behavior with a simple test case

Hook Configuration Structure

{
  "hooks": {
    "<EventName>": [
      {
        "matcher": "<ToolPattern>",
        "hooks": [
          {
            "type": "command",
            "command": "<shell-command>"
          }
        ]
      }
    ]
  }
}

Common Patterns

Reading Input Data

Hooks receive JSON via stdin. Use jq to extract fields:

# Extract tool input field
jq -r '.tool_input.file_path'

# Extract with fallback
jq -r '.tool_input.description // "No description"'

# Conditional processing
jq -r 'if .tool_input.file_path then .tool_input.file_path else empty end'

Exit Codes for PreToolUse

  • 0 - Allow the tool to proceed
  • 2 - Block the tool and provide feedback to Claude

Matcher Patterns

  • * - Match all tools
  • Bash - Match only Bash tool
  • Edit|Write - Match Edit or Write tools
  • Read - Match Read tool

Quick Examples

Log all bash commands:

jq -r '"\(.tool_input.command)"' >> ~/.claude/bash-log.txt

Auto-format TypeScript after edit:

jq -r '.tool_input.file_path' | { read f; [[ "$f" == *.ts ]] && npx prettier --write "$f"; }

Block edits to .env files:

python3 -c "import json,sys; p=json.load(sys.stdin).get('tool_input',{}).get('file_path',''); sys.exit(2 if '.env' in p else 0)"

Read the full file on GitHub · 89 lines

Files

What ships with it

2 files 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.

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.

  1. yesterday First seen · 89 lines · 83 tokens per session scan B d046588831ca

Subscribe to this mod's changes

hook-creator is a skill published in the GitHub repository greatSumini/cc-system (436 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 660 once invoked, about $0.0004 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens