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.
npx agentmods add instructions/steve-magne/hookstack/claude-mdgit clone --depth 1 https://github.com/steve-magne/hookstackWhat 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 | $0.09002 | $0.09002 |
| Opus 5 | $0.04501 | $0.04501 |
| Sonnet 5 | $0.01800 | $0.01800 |
| Haiku 4.5 | $0.00900 | $0.00900 |
Grade B, and why
hookstack CLAUDE.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `project` | (défaut) | `./.claude/settings.json` | claude (clé `hooks`) | conserve `$CLAUDE_PROJECT_DIR` | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Langage** : Node.js (`.mjs`) — OS-agnostique, disponible partout où `node` est dans le PATH. Pas de dépendances externes ; utiliser uniquement les builtins Node (`fs`, `child_process`, `path`). How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Présentation du projet
Hookstack est un catalogue communautaire de hooks agentiques multi-agent — Claude Code, OpenAI Codex et GitHub Copilot. Un hook est un script Node.js .mjs branché sur le cycle de vie de l'agent (PreToolUse, PostToolUse, SessionStart, Stop…) via un fichier de config — pas un plugin, pas un SDK, juste un événement.
Portabilité multi-agent : Codex et Claude Code partagent les mêmes noms d'événements de cycle de vie. Le code des hooks (.mjs) est donc identique entre agents — seul le format du fichier de config diffère : Claude Code/Copilot → .claude/settings.json ({ "hooks": { Event: [...] } }, scripts dans .claude/hooks/) ; Codex → .codex/hooks.json (événements à la racine, scripts dans .codex/hooks/). Le CLI gère cette transformation à l'installation (voir « Scopes d'installation CLI »). Un hook s'écrit une fois, se déploie sur les trois agents.
Promesse : "Get your HookStack in 1 minute" — un développeur arrive sur le site et peut immédiatement injecter une stack de hooks prédéfinis pour son type de projet via une seule commande npx. S'il le souhaite, il explore le catalogue, sélectionne des hooks plus spécifiques, copie la commande npx générée et les installe dans son projet.
Arrive → Stack prédéfinie (fast path) → npx hookstack-cli@latest install → Done
↓ optionnel
Browse catalogue + sélection fine → commande mise à jour → Done
Dogfood
Le projet est son propre cobaye. Les hooks de la collection (.claude/hooks/*.mjs) sont actifs sur ce dépôt via .claude/settings.json — ils sont exécutés à chaque session Claude Code sur ce projet, ce qui les valide en conditions réelles. Quand un .mjs est modifié, le hook registry-auto-sync.mjs (FileChanged) relance automatiquement node .claude/sync-hooks.mjs pour propager le code dans registry/registry.json (code_snippet). Le .mjs sur disque est la source de vérité du code ; le registre en est le reflet.
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.
- 2d ago First seen · 318 lines · 9,002 tokens per session scan B 6ef2e35a0d05
hookstack CLAUDE.md is an instructions file published in the GitHub repository steve-magne/hookstack (7 stars, last pushed 8d ago), licensed MIT. It adds 9,002 tokens to every session, about $0.0450 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.