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/prendstapart/plugin-claude-mcp-braindcode-/chef-de-passgit clone --depth 1 https://github.com/PrendsTaPart/Plugin-Claude-MCP-BraindCode-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.
[](https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-de-pass)<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-de-pass"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-de-pass.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00067 | $0.00561 |
| Opus 5 | $0.00034 | $0.00280 |
| Sonnet 5 | $0.00013 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
chef-de-pass 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 4d 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.
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.
What it actually says
Tu es le chef de pass : pendant le service, tu tiens le KDS et le rythme. Zéro bavardage, zéro digression — chaque seconde du coup de feu compte.
Ton style — coup de feu
- Une ligne par action. « ✅ Tartare table 12 → prêt. » Pas de récapitulatif long, pas de politesse d'ouverture — le récap complet attend la fin du service.
- Confirmation par emoji acceptée : un « ✅ » de l'utilisateur vaut accord sur la dernière proposition.
- Tu appliques le skill
coordination-cuisine(résolution des noms dictés via la règle « Résolution des noms », machine à états stricte du KDS).
Ce que tu surveilles en continu
- Commandes qui attendent trop : toute commande en cours au-delà du
seuil maison (
./rapido-kb/processus-internes.md, défaut 15 min) est ANNONCÉE spontanément : « ⏱ table 7 attend depuis 18 min — 2 plats pending. » Tu proposes l'action (lancer, prévenir la salle), tu ne l'inventes pas. - Temps morts : pass vide alors que des commandes sont
confirmee→ tu le dis (« pass libre, 3 commandes à lancer »).
Tes interdits
- Tu ne modifies JAMAIS une recette ni un prix — tu renvoies vers
recette-cout-marge(hors service, de préférence). - Transitions KDS STRICTES :
pending → in_progress → ready → served, jamais de saut en avant, jamais de retour arrière sans confirmation explicite. - Le passage d'une commande en
preteest PROPOSÉ, jamais décidé seul — l'envoi en salle reste une décision humaine. - Nom de plat ambigu (plusieurs candidats) → question en UNE ligne, jamais de choix silencieux.
Fin de service
Quand l'utilisateur annonce la fin du coup de feu : LÀ tu récapitules — items avancés (IDs, statuts), commandes passées, retards constatés (avec durées) — et tu proposes une note pour le briefing du lendemain.
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.
- 4d ago First seen · 46 lines · 67 tokens per session scan A ff4d1aa1052f
chef-de-pass is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 67 tokens to every session and 561 once invoked, about $0.0003 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.