A setup, diagnostic, and update workflow for project hooks: scripts that run automatically during coding or Git actions. It manages checks for security, code quality, formatting, tests, and commit messages.

Use it to set up, inspect, or refresh Claude Code hooks and Git pre-commit or commit-message checks, with support for project languages, tools, and repository structure.

It helps teams install or maintain automatic checks without losing track of existing hooks or project-specific settings.

hook-guard — Skill by musingfox

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/musingfox/cc-plugins/hook-guard

Any agent

npx skills add musingfox/cc-plugins --skill hook-guard

Clone the repo

git clone --depth 1 https://github.com/musingfox/cc-plugins

Made for: Claude Code, Codex.

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,126 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.

Model	Per session	Once invoked
Fable 5	$0.00112	$0.01126
Opus 5	$0.00056	$0.00563
Sonnet 5	$0.00022	$0.00225
Haiku 4.5	$0.00011	$0.00113

Measured yesterday against content hash 68414f821dc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hook-guard 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 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.

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.

hook-guard/skills/hook-guard/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hook Guard

Dispatch by user intent:

Setup — install is missing or user asks to set up / configure / initialize
Doctor — user asks to check / diagnose / verify / troubleshoot
Update — install exists and user asks to update / refresh / regenerate / sync

If ambiguous: if .githooks/pre-commit exists and .claude/settings.local.json has hook-guard hooks → default to Doctor; otherwise → Setup.

Read references/settings.md for the user-override schema (.claude/hook-guard.local.md) — applies to all three modes.

Setup

Skip if the user only wants to edit existing hooks. If jj-native only (no .git/), abort — pre-commit hooks not supported.

Detect — follow references/detection.md. Collect: languages, toolchain, VCS, existing hooks, monorepo. If existing hooks found, ask merge / replace / abort.
Recommend — read .claude/hook-guard.local.md if present. Present summary grouped by: CC hooks (PostToolUse lint/format soft, PreToolUse test gate hard), pre-commit always-run (security / integrity / structure), pre-commit skippable (lint / format / test), commit-msg. Ask to confirm.
Generate:
- .githooks/pre-commit from references/pre-commit-checks.md — only enabled checks, real tool commands substituted. chmod +x.
- .githooks/commit-msg from references/commit-msg.md if enabled. chmod +x.
- .claude/settings.local.json — merge (not overwrite) hooks + env.CLAUDECODE=1 per references/cc-hooks.md.
- Run git config core.hooksPath .githooks.
- Ensure .claude/*.local.md gitignored.
Summary — files touched, onboarding cmd (git config core.hooksPath .githooks), mention Doctor / Update modes.

Doctor

Run all checks, present a status table (✓ / ✗ / ⚠ / ℹ), then offer auto-fix for FAIL/WARN.

git config core.hooksPath — must equal .githooks. Unset = FAIL. Other = WARN.
Hook files — .githooks/pre-commit and (if conventional commits) .githooks/commit-msg: exist + executable.
.claude/settings.local.json — hooks.PostToolUse with Edit|Write matcher; hooks.PreToolUse with Bash matcher; env.CLAUDECODE == "1".
Tools — grep pre-commit + CC hooks for tool names (ruff, eslint, prettier, gitleaks, jq, python3…); command -v each.
CLAUDECODE skip — grep -q 'CLAUDECODE' .githooks/pre-commit. Missing = WARN.
Settings file — validate .claude/hook-guard.local.md frontmatter (schema in references/settings.md); warn on unknown fields.
(Optional) Dry-run — offer to execute .githooks/pre-commit on current tree.

Read the full file on GitHub · 79 lines

Files

What ships with it

5 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.

yesterday First seen · 79 lines · 112 tokens per session scan A 68414f821dc4

Subscribe to this mod's changes

hook-guard is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 1,126 once invoked, about $0.0006 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 2026-08-31.

Code review Debugging Testing

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