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/integrer-un-outil/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/integrer-un-outil)<a href="https://agentmods.dev/skills/ai-swiss/base/integrer-un-outil"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/integrer-un-outil/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/integrer-un-outil"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/integrer-un-outil.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 | $0.00845 |
| Opus 5 | $0.00028 | $0.00423 |
| Sonnet 5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
integrer-un-outil 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intégrer BASE à un outil
Le principe reste le même pour tous les outils; seuls les détails changent. Ton rôle: poser ce principe, puis l'adapter à l'outil précis de l'utilisateur en t'appuyant sur sa documentation.
Sources à lire d'abord
docs/reference/base-et-vos-outils-ia.md(le principe: couche d'intelligence possédée vs exécution; agents planifiés; la couture de vérification)mcp/README.md(comment exposer et appeler le serveur MCP de BASE)
Étapes
- Identifier l'outil. Demande à l'utilisateur de quel outil ou plateforme il s'agit (planificateur, plateforme d'agents, suite IA), et ce qu'il veut faire (agent planifié, autonome, simple connexion).
- Obtenir la documentation de l'outil.
- Demande un lien vers la documentation d'intégration de cet outil (déclencheurs planifiés, agents, support de MCP, étapes de validation humaine).
- Si ton environnement permet la navigation web, propose de la chercher toi-même, puis fais valider la source à l'utilisateur.
- Ne devine pas les capacités d'un produit: appuie-toi sur sa documentation à jour, et signale ce que tu n'as pas pu vérifier.
- Adapter le principe générique (de
base-et-vos-outils-ia.md) à cet outil, couche par couche:- le planificateur de l'outil lance l'exécution;
- l'agent d'exécution appelle le serveur MCP de BASE pour obtenir le process et ses ressources;
- la génération s'appuie sur le modèle et les connecteurs de l'outil;
- aux points de décision, l'agent s'arrête pour validation humaine (repère le mode «brouillon» ou «exiger une approbation» de l'outil);
- après approbation, l'écriture est appliquée (proposition puis application côté BASE).
- Garder la couture de vérification. Rappelle la règle: la génération peut être automatique, la validation reste tenue par un humain. Aide l'utilisateur à calibrer, étape par étape, ce qui s'automatise et ce qui attend une approbation.
- Donner des étapes concrètes et vérifiables, dans l'ordre, propres à l'outil, et proposer un premier essai à faible risque (mode brouillon).
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 · 55 lines · 55 tokens per session scan A ac27e4a1a7a9
integrer-un-outil is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 6d ago), licensed Apache-2.0. It adds 55 tokens to every session and 845 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.