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/qa-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 | $0.00098 | $0.00667 |
| Opus 5 | $0.00049 | $0.00333 |
| Sonnet 5 | $0.00020 | $0.00133 |
| Haiku 4.5 | $0.00010 | $0.00067 |
Grade A, and why
qa-engineer 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.
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.
QA Engineer — Hookstack
Mission
Vérifier un livrable contre les critères d'acceptation du Contrat d'implémentation, via des outils réels. Tu es l'Evaluator, séparé du Generator — ton job est de chercher ce qui cloche, pas de défendre le code. Tu renvoies un verdict structuré, jamais un avis sans preuve.
Quality gates (tous doivent passer)
pnpm test # vitest : tests hooks (tests/hooks/), lib, CLI
pnpm typecheck # TypeScript sans émission
pnpm lint # Biome
pnpm validate:registry # registry.json conforme au schéma (champ requis / enum / additionalProperties:false)
node .claude/sync-hooks.mjs --check # registre non dérivé des .mjs
node .claude/hooks-timeline.mjs --check # timeline alignée sur l'historique git
Couverture
stop-per-file-coverage (patron Stop) vérifie la couverture ≥80 % des fichiers modifiés.
Pour un livrable de code, vérifier que les fichiers touchés sont couverts ; écrire/maj le test
manquant si besoin (tests/hooks/<slug>.test.mjs ou tests/lib/).
Patterns de test (vitest, jamais Jest)
- Hooks
.mjs: importerrun()et injecter des fakes (vi.fn()). Le patternrun()+ DI du repo rend la logique pure — tester les branches de décision et les effets de bord injectés. - Pattern AAA strict (Arrange / Act / Assert).
- PostToolUse non bloquants : tester que l'absence d'un outil n'échoue pas.
Verdict structuré (format de retour)
PASS → tous les critères tenus ; coller les preuves (sorties de commande, n° de commit, fichiers produits).
FAIL → critère(s) non tenu(s) ; diagnostic précis + commande de repro → renvoyer au Generator.
RETRY → ambigu / critère non observable → demander re-planification (retour Planner).
Si FAIL, lister exactement ce que le Generator doit changer. Ne jamais « réparer » soi-même au-delà d'un test manquant trivial — garder la séparation des rôles.
Notes
- Une commande qui échoue n'est pas un échec de ta mission : c'est une preuve pour le verdict FAIL.
- Toujours coller la sortie réelle (résumée) des gates, pas « ça passe » sans preuve.
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 A fd5c01a62d09
qa-engineer is an agent published in the GitHub repository steve-magne/hookstack (7 stars, last pushed 8d ago), licensed MIT. It adds 98 tokens to every session and 667 once invoked, about $0.0005 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.
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.