hooks-and-enforcement

hooks-and-enforcement is a skill for Claude Code from mlopscommunity/Coding-Agents-Conference-skills. It costs 43 tokens per session (3,253 once invoked), scanned B, original, Apache-2.0.

A setup for Claude Code lifecycle hooks, which are automatic checks that run at defined points and can stop an agent when required rules fail.

In plain words
What is it for?
Use it to configure mandatory quality or security checks, audit agent commands, manage permission prompts, and protect files or tests from modification.
Why use it?
It enforces tests, linting, compilation, security checks, protected files, and command logging instead of relying only on written instructions.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is "command": "bash -c 'INPUT=$(cat); if echo \"$INPUT\" | grep -q \"git commit\"; then bash .claude/hooks/pre-commit-checks.sh; fi'".

Good fit Use it to configure mandatory quality or security checks, audit agent commands, manage permission prompts, and protect files or tests from modification.

Compare 6 skills from other repositories ↓
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/mlopscommunity/Coding-Agents-Conference-skills
agentmods
npx agentmods add skills/mlopscommunity/coding-agents-conference-skills/hooks-and-enforcement

Made for: Claude Code.

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.

agentmods badge for hooks-and-enforcement

README.md
[![agentmods](https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/hooks-and-enforcement/github.svg)](https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/hooks-and-enforcement)
Your own site
<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/hooks-and-enforcement"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/hooks-and-enforcement/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.

agentmods 80×15 button for hooks-and-enforcement

Your own site · 80×15
<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/hooks-and-enforcement"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/hooks-and-enforcement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.03253
Opus 5 $0.00022 $0.01626
Sonnet 5 $0.00009 $0.00651
Haiku 4.5 $0.00004 $0.00325

Measured 10d ago against content hash 80f56452f979, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

hooks-and-enforcement scanned grade B with 3 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 10d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

if echo "$COMMAND" | grep -qE "(rm -rf /|sudo|chmod 777|curl.*\| bash)"; then

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

if echo "$COMMAND" | grep -qE "(rm -rf /|sudo|chmod 777|curl.*\| bash)"; then

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

if echo "$COMMAND" | grep -qE "(rm -rf /|sudo|chmod 777|curl.*\| bash)"; then
skills/hooks-and-enforcement/SKILL.md · 405 lines

How it starts

The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hooks and Enforcement

Overview

Lifecycle hooks are the mechanism for enforcing rules that an AI agent must follow without exception. While CLAUDE.md instructions guide behavior, they are suggestions the agent can interpret loosely or skip. Hooks are enforcement -- they run automatically at defined points in the agent's lifecycle and block progress when checks fail.

Core principle: Instructions in CLAUDE.md are suggestions; hooks are enforcement. Use hooks for anything that MUST happen.

Dependency: Claude Code with settings.json hook configuration. Security scanning tools (e.g., Semgrep) for code analysis hooks.

When to Use

  • When you need linting, tests, or compilation to pass before every commit
  • When agent-generated code must be scanned for security vulnerabilities before shipping
  • When you need an audit trail of every shell command the agent runs
  • When you want automated approval of safe permission prompts to reduce friction
  • When you have tests or files the agent must never modify

When NOT to Use

  • For stylistic preferences or soft guidelines (put those in CLAUDE.md)
  • For checks that are slow and disruptive when run on every edit (use pre-commit instead)
  • When the project has no CI/CD and no quality requirements

Common Mistakes

Mistake Why it's wrong
Putting critical rules only in CLAUDE.md CLAUDE.md is advisory. The agent can misinterpret or skip instructions. Hooks enforce mechanically -- they cannot be bypassed.
Using per-edit hooks for slow operations like full test suites Per-edit hooks fire constantly and destroy flow. Sid: pre-commit hooks are preferred because they are "less disruptive to flow." Reserve per-edit for fast checks only.
Letting the agent modify its own test files The agent will "fix" failing tests by weakening assertions. Create immutable test files the agent cannot touch. Josh: "Create immutable tests the agent cannot modify."
Skipping audit logging for agent sessions Without an audit trail you cannot debug what went wrong. Log every shell command with timestamp. Milan: "You need to know what the agent did and when."
Running security scans only in CI Agent-generated code can introduce vulnerabilities locally before it ever reaches CI. Scan before commit so vulnerabilities never enter the repo.

Read the full file on GitHub · 405 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. 10d ago First seen · 405 lines · 43 tokens per session scan B 80f56452f979

Subscribe to this mod's changes

hooks-and-enforcement is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (37 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 3,253 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, makes network calls). 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens