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 skills add ai-swiss/base --skill metier-reuniongit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/skills/ai-swiss/base/metier-reunion)<a href="https://agentmods.dev/skills/ai-swiss/base/metier-reunion"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/metier-reunion/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/skills/ai-swiss/base/metier-reunion"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/metier-reunion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01519 |
| Opus 5 | $0.00028 | $0.00759 |
| Sonnet 5 | $0.00011 | $0.00304 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
metier-reunion 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 11d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Métier: Compte-rendu de réunion
Savoir-faire pour rédiger des comptes-rendus de réunion clairs, neutres et utiles, à destination des PME, des équipes et des indépendants.
Anatomie d'un bon compte-rendu
Un compte-rendu utile contient, dans l'ordre:
- En-tête: titre ou type de réunion, date, heure, lieu (ou «à distance»)
- Participants: présents, excusés, et qui a rédigé le compte-rendu
- Ordre du jour: la liste des sujets abordés
- Pour chaque sujet:
- un bref rappel du point discuté (factuel, neutre)
- les décisions prises
- les actions décidées (avec responsable et échéance)
- les informations partagées
- Tableau récapitulatif des actions: action, responsable, échéance, statut
- Prochaine réunion: date et sujets pressentis, si connus
Qualités d'un bon compte-rendu
- Fidèle: il reflète ce qui s'est dit, sans ajout ni omission importante.
- Neutre: il ne juge pas, ne prend pas parti, n'embellit pas.
- Concis: il va à l'essentiel. Un compte-rendu n'est pas une transcription mot à mot.
- Actionnable: après lecture, chacun sait qui fait quoi, et pour quand.
- Traçable: décisions et actions sont identifiables et retrouvables.
Distinguer décision, action et information
C'est le cœur du métier. Trois catégories qu'il ne faut jamais confondre:
| Catégorie | Définition | Signe distinctif |
|---|---|---|
| Décision | Un choix arrêté collectivement | «Il est décidé que...», «Nous retenons l'option B», un vote, un accord explicite |
| Action | Une tâche concrète à réaliser | Un verbe d'action, un responsable, une échéance: «Marie envoie le devis avant vendredi» |
| Information | Un élément partagé, sans choix ni tâche | «Le chiffre d'affaires a progressé de 4%», un point de situation, une annonce |
Règles de classement
- Une discussion n'est pas une décision. Tant qu'aucun choix n'est arrêté, il s'agit d'une information ou d'un débat en cours. En cas de doute:
[A VALIDER: était-ce une décision ?]. - Une intention n'est pas une action. «Il faudrait peut-être contacter le fournisseur» ne devient une action qu'une fois un responsable désigné. Sinon:
[A COMPLETER: responsable ?]. - Une décision peut donner lieu à une action. «Décision: on lance le projet (action: Paul prépare le planning pour le 15)». On note les deux.
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.
- 11d ago First seen · 101 lines · 55 tokens per session scan A 3e8d32ce4671
metier-reunion is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 7d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,519 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 2026-08-30.
Other skills, from other repositories
wallet-cli
Operate the TypeScript TRON wallet CLI for accounts, transfers, staking, governance, contracts, signing, chain queries, and password input with wallet-cli 4.13.0. Refuse wallet passwords in argv and require the supported stdin channel. For Java REPL requests, refuse that entry and offer the TypeScript one-shot CLI…
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
vault
Operate Joel's Obsidian Vault through the joelclaw CLI. Use when reading ADRs/projects, searching notes, listing PARA sections, or auditing ADR hygiene with vault adr commands. Triggers on: 'check the vault', 'read ADR', 'find this note', 'vault search', 'ADR collisions', 'ADR audit', 'decision inventory', or any…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.