Borrowing it
Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/concierge-base/skills/processes/fiche-de-decision/SKILL.mdgit 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/fiche-de-decision)<a href="https://agentmods.dev/skills/ai-swiss/base/fiche-de-decision"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/fiche-de-decision/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/fiche-de-decision"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/fiche-de-decision.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 | $0.00042 | $0.00763 |
| Opus 5 | $0.00021 | $0.00381 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
fiche-de-decision 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 10d 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
Fiche de décision
Quand plusieurs choix sont ouverts, une fiche vaut mieux qu'un fil de discussion: la personne y note chaque point, le commente, puis vous renvoie l'ensemble d'un coup. La personne décide; la fiche structure la décision.
Étapes
- Lister les vraies décisions. Une carte par point. Chaque carte: le contexte, votre recommandation (mettez-la en tête) et, si utile, votre lecture préalable. N'y ajoutez pas de points déjà réglés.
- Construire depuis le modèle. Copiez le modèle de l'agent,
.ai/agents/concierge-base/templates/decision-sheet.html, vers.temp/{AAAA-MM-JJ}_{sujet}/{AAAA-MM-JJ}_{sujet}_decisions.html, un radical daté, unique par fiche. Renseignez le titre, l'intro, le tableauPOINTS(id,title,what,reco,recoSummary,scaleLabel), et les deux noms qui apparient la fiche vierge et son retour:STORAGE_KEY={AAAA-MM-JJ}_{sujet}_decisions(nomme la sauvegarde navigateur) etEXPORT_FILE={AAAA-MM-JJ}_{sujet}_decisions-filled.md(l'export se range ainsi à côté de sa fiche vierge et reste lisible hors de son dossier). - Rester sobre. Pas de référence à un cadre externe; le style est déjà dans le modèle.
.temp/est ignoré par git, la fiche reste un brouillon. - Ouvrir la fiche pour la personne et attendre. La fiche s'enregistre dans le navigateur; l'export est un Markdown qu'elle vous rend.
- Agir sur l'export. Appliquez là où elle est d'accord, suivez ses commentaires là où elle nuance, gardez votre recommandation là où elle n'a pas répondu (et dites-le). Si une décision mérite d'être conservée, proposez d'en faire une courte note écrite.
Ce que vous ne faites jamais
- Décider à la place de la personne, ou transformer une abstention honnête en choix forcé.
- Rouvrir des points déjà réglés, ou noyer la recommandation sous le contexte.
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.
- 10d ago First seen · 58 lines · 42 tokens per session scan A d0ee6e497eda
fiche-de-decision is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 6d ago), licensed Apache-2.0. It adds 42 tokens to every session and 763 once invoked, about $0.0002 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.