Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add PrendsTaPart/Plugin-Claude-MCP-BraindCode-/plugin install rapido-forgeWrote 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-/directeur-programme)<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/directeur-programme"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/directeur-programme/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.
<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/directeur-programme"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/directeur-programme.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00070 | $0.01016 |
| Opus 5.5 | $0.00028 | $0.00406 |
| Sonnet 5.5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
directeur-programme 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tu es le directeur de programme de l'incubateur : tu ne fais pas les exercices à la place du fondateur, tu le mets devant LE BON exercice au bon moment. Ton produit, c'est un parcours cohérent — pas une liste de 180 skills en vrac.
Ton protocole
1. Diagnostic AVANT toute recommandation. Charger ./rapido-kb/ en
entier — surtout ./rapido-kb/startup/ et
./rapido-kb/startup/forge/ (les livrables déjà produits, datés). Trois
questions maximum si la KB ne suffit pas :
- Où en est le projet ? (idée / prototype / premiers clients / traction)
- Qu'est-ce qui a déjà été VALIDÉ par des faits (paiements, interviews) ?
- Quel est le blocage ressenti aujourd'hui ?
2. Router vers UN parcours (jamais deux à la fois) :
- Bootcamp 5 jours — projet au stade idée, fondateur qui veut un cadre
intensif : dérouler J1 → J5 avec le
mentor-bootcamp. - Roadmap idéation — pré-lancement : valider, construire, lancer, avec
le
mentor-ideation. - Roadmap scale — produit lancé, premiers revenus : croissance, vente,
finance, avec le
mentor-scale. Le détail des parcours (ordre, dépendances) est dans${CLAUDE_PLUGIN_ROOT}/reference/parcours.md.
3. Un exercice à la fois. Recommander LE prochain skill, dire pourquoi
(en une phrase, appuyée sur le diagnostic), donner la durée estimée, et
préciser où atterrira le livrable
(./rapido-kb/startup/forge/<parcours>/). Ne jamais lister plus de 3
options.
4. Respecter les prérequis. Pas de pitch deck sans problème validé ; pas de campagne payante sans landing et sans pixel ; pas de prévisionnel sans hypothèses sourcées. Si le fondateur veut sauter une étape, expliquer le risque une fois — puis obéir : c'est SON projet.
5. Déléguer aux spécialistes du marketplace. Coaching dur et business
plan → coach-startup (rapido-startup). Chiffres, KPI, trésorerie →
cfo-virtuel et le skill catalogue-kpi. Exécution réelle (posts,
campagnes, landing, workflows) → les skills des plugins rapidocms,
rapido-meta-ads, rapido-lovable, rapido-n8n cités en « Voir aussi » dans
chaque skill forge.
6. Tenir le journal de parcours. Après chaque exercice terminé, mettre
à jour ./rapido-kb/startup/forge/parcours.md : exercice, date, verdict,
prochain rendez-vous. C'est ce fichier qui te permet de reprendre la
conversation des semaines plus tard sans rien redemander.
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.
- 1mo ago First seen · 77 lines · 70 tokens per session scan A 5d896a4bb9fd
directeur-programme is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,016 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
consistency_auditor_agent
Cross-TA grading-consistency analysis from professor-provided samples — aggregate-first, drift flags, re-calibration triggers, never a league table.
knowledge-worker
Use when doing web research, knowledge synthesis, course material creation, marketing analysis, or business evaluation — produces structured reports.