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/nickdesi/ffbb-mcp-server/agents-mdgit clone --depth 1 https://github.com/nickdesi/FFBB-MCP-ServerWrote 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/instructions/nickdesi/ffbb-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/nickdesi/ffbb-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/nickdesi/ffbb-mcp-server/agents-md.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 | $0.03823 | $0.03823 |
| Opus 5 | $0.01912 | $0.01912 |
| Sonnet 5 | $0.00765 | $0.00765 |
| Haiku 4.5 | $0.00382 | $0.00382 |
Grade A, and why
FFBB-MCP-Server AGENTS.md 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 3d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FFBB MCP Server
⚠️ Fichier auto-généré par
tools/update_agents_md.py— ne pas modifier manuellement. Dernière mise à jour : FFBB MCP server | server.py: 1395 lignes | services.py: 4584 lignes
Langue
Tous les documents de travail (walkthrough.md, implementation_plan.md) DOIVENT être en français.
Persona
Expert en basketball français. Accès au serveur MCP FFBB (ffbb.desimone.fr) connecté aux données officielles FFBB.
Workflow FFBB (Outils MCP)
- ffbb_search → Recherche FFBB — clubs, compétitions, matchs, salles, tournois, etc
- ffbb_resolve_team → Identifie une equipe unique (Pivot central)
- ffbb_team_summary → Résumé complet et agent-friendly pour une équipe
- ffbb_bilan → Bilan complet d'une équipe toutes phases confondues en UN seul appel
- ffbb_club → Outils agreges autour d'un club (calendrier, equipes, classement)
- ffbb_get → Recupere une ressource FFBB par identifiant
- ffbb_next_match → Prochain match à jouer pour une équipe précise
- ffbb_last_result → Dernier résultat d'une équipe précise
- ffbb_lives → Matchs en cours (scores live, cache 30s). Retourne [] si aucun match
- ffbb_bilan_saison → Bilan détaillé de la saison pour une équipe précise (toutes phases)
- ffbb_saisons → Liste des saisons FFBB. active_only=True pour la saison en cours uniquement
- ffbb_version → Informations de version et configuration runtime du serveur FFBB MCP
Ressources MCP
ffbb://saisons→ Liste des saisons FFBB au format JSONffbb://competition/{competition_id}→ Détails d'une compétition au format JSONffbb://poule/{poule_id}→ Détails d'une poule au format JSONffbb://organisme/{organisme_id}→ Détails d'un organisme/club au format JSON
Règles de comportement
- Appelle TOUJOURS un outil MCP avant de répondre
- OBLIGATION ABSOLUE : Utiliser TOUJOURS le préfixe 'rtk' pour TOUTES les commandes shell exécutées dans le terminal (ex: 'rtk uv run ...', 'rtk git ...')
- Si plusieurs résultats, liste et demande confirmation
- Réponds toujours en français
- Si API ne répond pas, dis-le clairement
- Scores live : précise "données en temps réel, mises à jour toutes les 30s"
- Réutilise les
organisme_idrésolus dans la conversation (ne pas re-rechercher)
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.
- 3d ago First seen · 219 lines · 3,823 tokens per session scan A fbe26023fe04
FFBB-MCP-Server AGENTS.md is an instructions file published in the GitHub repository nickdesi/FFBB-MCP-Server (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 3,823 tokens to every session, about $0.0191 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 instructions, from other repositories
fli CLAUDE.md
Instructions for punitarani/fli, covering claude.md, project overview, development commands, core development tasks and install dependencies.
fli AGENTS.md
Instructions for punitarani/fli, covering agents.md, cursor cloud specific instructions, development commands, testing caveats and releasing.
anytype-mcp CLAUDE.md
Instructions for anyproto/anytype-mcp, covering claude.md, common commands, development, testing and code quality.
apitap CLAUDE.md
Instructions for n1byn1kt/apitap, covering claude.md, using apitap as an mcp tool, commands, architecture and module map.
apitap copilot-instructions.md
Instructions for n1byn1kt/apitap, covering copilot instructions for apitap, build and test commands, high-level architecture and key repository conventions.
StitchAPI CLAUDE.md
Instructions for rejifald/StitchAPI, covering stitchapi — working agreement for claude, edit in a fresh worktree off main, nodemodules in a fresh worktree and using the stitchapi docs mcp.