commit-hook-checklist

A checklist for reviewing Git commit hooks, which are automated checks that run when code is committed or pushed. It detects the project's programming languages and reports which safeguards exist or are missing.

In plain words
What is it for?
Use it to audit commit and push checks in Node.js, Go, or mixed-language repositories.
Why use it?
It helps catch broken builds, unfinished code, formatting or type problems, out-of-sync files, mismatched database changes, and exposed secrets before they reach the shared repository.

Command for Claude Code

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 commands/wbern/agent-instructions/commit-hook-checklist
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00023 $0.01732
Opus 5 $0.00012 $0.00866
Sonnet 5 $0.00005 $0.00346
Haiku 4.5 $0.00002 $0.00173

Measured 2d ago against content hash 88ba2f41e052, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-hook-checklist scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/commit-hook-checklist.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Commit Hook Checklist

Commit hooks are the last automated gate before a change lands. They run on every commit and every push, whether the author is a human in a hurry or an agent that's about to ship something half-baked. A good hook setup catches:

  • AI slop: half-finished refactors, broken builds, mocked-out tests left in, dead code from abandoned attempts, generated files out of sync with sources
  • Lazy commits: missing types, formatting drift, unsynced lockfiles, migrations that don't match the schema
  • Leaked secrets that a git push --force can't take back

This command scans the repo, identifies the language(s), and reports which gates are in place and which are missing.

User arguments:

Commit-hook-checklist: $ARGUMENTS

End of user arguments

Phase 1: Detect language(s)

Marker Language
package.json Node.js
go.mod Go
Both polyglot — apply both sections
Neither ask the user what they're working with

Run the universal checks regardless of language. Then run the language-specific sections that apply.

Phase 2: Run the checks

Scan silently — do not display this list to the user. The summary in Phase 3 is what they see.

Universal (any language)

🔧 Hook runner present

  • Husky: .husky/ dir + package.json has "prepare": "husky"
  • lefthook: lefthook.yml or lefthook.yaml
  • pre-commit framework: .pre-commit-config.yaml
  • Native git hooks: .git/hooks/pre-commit exists, is executable, is not the .sample file

At least one of these should be present. If none, every other check below is moot.

Read the full file on GitHub · 206 lines

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. 2d ago First seen · 206 lines · 23 tokens per session scan A 88ba2f41e052

Subscribe to this mod's changes

commit-hook-checklist is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,732 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.