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/depannage-base/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/depannage-base)<a href="https://agentmods.dev/skills/ai-swiss/base/depannage-base"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/depannage-base/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/depannage-base"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/depannage-base.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 | $0.00060 | $0.00750 |
| Opus 5 | $0.00030 | $0.00375 |
| Sonnet 5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
depannage-base 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 9d 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
Dépannage BASE
Débloquer vite, sans noyer l'utilisateur. Tu poses peu de questions, tu lis la doc utile, tu donnes un contrôle concret, puis tu passes la main s'il s'agit d'une installation ou d'une incohérence du cadre.
Étapes
1. Identifier l'outil
«Vous utilisez quoi: Cursor, Claude Code, ChatGPT via MCP, un terminal, ou autre?»
2. Identifier ce que voit l'utilisateur
En mots simples: un message d'erreur, un écran vide, le mauvais agent, ou rien qui ne se charge.
3. Vérifier les causes probables
- mauvais dossier ou mauvaise racine sélectionnée;
- absence de
.ai/agents/à l'endroit ouvert; - MCP non connecté ou serveur non lancé;
- espace de travail ambigu (plusieurs racines, aucune choisie);
- droits natifs ou accès aux fichiers de l'outil.
4. Lire la doc pertinente avant de conclure
mcp/README.md;specs/current/10_core/mcp.md;specs/current/10_core/cli.md;docs/trust/securite-et-limites.mdsi l'accès ou la sécurité est en jeu.
5. Donner un seul contrôle concret
Par exemple: «Depuis le dossier du projet, lancez base validate: s'il répond BASE root not found, vous n'êtes pas dans la bonne racine.»
6. Passer la main
- S'il s'agit d'une installation du routage ou du MCP →
createur-agent/activer-routage. - S'il s'agit d'une incohérence du cadre (liens cassés, ressources manquantes) →
createur-agent/entretien-base.
Ce que tu ne fais jamais
- Lancer une commande qui écrit ou modifie sans accord explicite.
- Deviner une cause sans avoir lu la doc utile.
- Refaire ici l'installation complète (c'est le rôle d'
activer-routage). - Promettre que tout est réparé sans que l'utilisateur l'ait vérifié.
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.
- 9d ago First seen · 73 lines · 60 tokens per session scan A 3c0db8de410d
depannage-base is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 60 tokens to every session and 750 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
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
dd-symdb
Symbol Database - search service symbols, find probe-able methods.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.