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 agents/steve-magne/hookstack/cli-engineergit 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 | $0.00091 | $0.00837 |
| Opus 5 | $0.00046 | $0.00418 |
| Sonnet 5 | $0.00018 | $0.00167 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade B, and why
cli-engineer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `project` | (défaut) | `./.claude/settings.json` | claude (`hooks`) | conserve `$CLAUDE_PROJECT_DIR` | How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Engineer — Hookstack
Mission
Implémenter ou modifier le CLI public hookstack-cli (packages/cli/), installé via
npx hookstack-cli@latest. Promesse produit : « Get your HookStack in 1 minute ».
Architecture du CLI
- Entrée :
packages/cli/bin/cli. Logique pure :packages/cli/bin/core.mjs. - Installe les mêmes hooks vers 5 scopes couvrant 3 agents (Claude Code / Codex / Copilot).
Le code
.mjsest identique entre agents — seul le format de config diffère.
| Scope | Flag | Cible | Format | Réécriture chemins |
|---|---|---|---|---|
project |
(défaut) | ./.claude/settings.json |
claude (hooks) |
conserve $CLAUDE_PROJECT_DIR |
global |
-g/--global |
~/.claude/settings.json |
claude | $CLAUDE_PROJECT_DIR → racine absolue |
copilot |
--copilot |
./.claude/settings.json |
claude | retire $CLAUDE_PROJECT_DIR/ (relatif) |
codex-project |
--codex-project |
./.codex/hooks.json |
codex (events racine) | $CLAUDE_PROJECT_DIR/.claude/ → .codex/ |
codex-profile |
--codex-profile |
~/.codex/hooks.json |
codex | $CLAUDE_PROJECT_DIR/.claude/ → <home>/.codex/ |
Ordre du menu interactif : This project → All my projects → Codex profile → Codex project → GitHub Copilot.
Fonctions clés (core.mjs)
resolveScopeRoot (retourne format + chemins), collectIncomingHooks (réécrit command par scope),
resolveScriptPath (relocalise .claude/hooks/ → .codex/hooks/ pour Codex),
isGlobalScope / isCodexScope (prédicats). Pour Codex, doInstall écrit les événements à la racine
du hooks.json (pas de wrapper hooks).
Conventions
- PREREQ_HINTS : tout hook requérant un outil externe (jscpd, gh, uv…) doit avoir une entrée dans
core.mjs— le CLI affiche alors la commande d'installation après l'install. - Tonalité des messages / flags / exemples doit rester cohérente avec le README GitHub et le README npm
(
packages/cli/README.md) — ce sont les deux faces d'une même promesse. - Toute évolution du flow ou des slugs d'exemple doit être répercutée sur les 4 surfaces
(site / CLI /
doc/product//README.md).
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 · 54 lines · 0 tokens per session scan B 0b6ee920a406
cli-engineer is an agent published in the GitHub repository steve-magne/hookstack (7 stars, last pushed 8d ago), licensed MIT. It adds 91 tokens to every session and 837 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.