le-cabinet: Instructions file for Claude Code

AGENTS.md

le-cabinet AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Sjrazaviebra/le-cabinet. It costs 1,466 tokens per session, scanned A, original, MIT.

A guide to using the le-cabinet repository with different coding agents. It separates reusable Markdown, JSON, and Python content from Claude Code-specific setup.

In plain words
What is it for?
Use it to choose among seven roles, load the right instructions, and understand which files and scripts work across agents. It also explains what must be connected manually outside Claude Code.
Why use it?
It helps you reuse the repository with tools such as Cursor, Copilot, Windsurf, custom GPTs, or local models without confusing portable content with Claude-only features.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is Sjrazaviebra/le-cabinet's own configuration. It tells Claude Code, Codex and OpenCode how to work on le-cabinet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything le-cabinet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Sjrazaviebra/le-cabinet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Sjrazaviebra/le-cabinet/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Sjrazaviebra/le-cabinet

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for le-cabinet AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sjrazaviebra/le-cabinet/agents-md/github.svg)](https://agentmods.dev/instructions/sjrazaviebra/le-cabinet/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sjrazaviebra/le-cabinet/agents-md"><img src="https://agentmods.dev/badge/instructions/sjrazaviebra/le-cabinet/agents-md/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.

agentmods 80×15 button for le-cabinet AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sjrazaviebra/le-cabinet/agents-md"><img src="https://agentmods.dev/badge/instructions/sjrazaviebra/le-cabinet/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,466 This file is loaded in full into every session.
When invoked 1,466 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01466 $0.01466
Opus 5 $0.00733 $0.00733
Sonnet 5 $0.00293 $0.00293
Haiku 4.5 $0.00147 $0.00147

Measured 9d ago against content hash 959efbbfc602, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

le-cabinet 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 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.

AGENTS.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — utiliser ce dépôt avec n'importe quel agent

Ce dépôt est packagé pour Claude Code (skills et plugins), mais son contenu n'a rien de propriétaire : ce sont des fichiers Markdown et JSON. Ce fichier explique comment s'en servir ailleurs — Cursor, Copilot, Windsurf, un GPT personnalisé, un RAG maison, un modèle local.

Ce qui est portable, et ce qui ne l'est pas

Portable partout Propre à Claude Code
Les 61 fichiers references/*.md — aucune syntaxe spécifique à l'intérieur Le frontmatter YAML de SKILL.md (name, description)
Les 7 data/parametres.json — sources et dates lisibles par n'importe quel outil, et catalogue.json — l'index des neuf rôles, sans syntaxe propriétaire .claude-plugin/plugin.json et .claude-plugin/marketplace.json
Les scripts de scripts/ — Python standard, aucune dépendance Le routage automatique : Claude lit la description et charge le bon rôle seul

⇒ Ailleurs, le contenu marche tel quel ; c'est l'aiguillage qu'il faut refaire à la main. Le frontmatter YAML est inoffensif : les autres outils l'ignorent.

Les sept rôles, et lequel charger

Rôle Charger quand la question porte sur…
comptable une entreprise : forme juridique, micro, TVA, facturation, paie, clôture
impots un particulier : déclaration, barème, placements, immobilier, IFI, contrôle
juriste l'activité : contrats, sociétés, données personnelles, consommation, procédure
travail un salarié : contrat, rupture, salaire, congés, harcèlement, prud'hommes
logement un bail : entrée, charges, congé, dépôt de garantie, impayés, copropriété
famille le couple et la filiation : union, séparation, enfants, succession, protection
immigration le séjour : titres, travail, famille, recours, naturalisation
financement l'argent de l'activité : compte pro et droit au compte, crédit et rupture de crédit, caution du dirigeant, trésorerie, médiation du crédit, assurances obligatoires
patrimoine l'argent personnel : arnaques et vérification d'un agrément, enveloppes et supports, frais, risque et horizon, épargne réglementée, retraite, budget et surendettement

Read the full file on GitHub · 93 lines

Changes

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.

  1. 9d ago First seen · 93 lines · 1,466 tokens per session scan A 959efbbfc602

Subscribe to this mod's changes

le-cabinet AGENTS.md is an instructions file published in the GitHub repository Sjrazaviebra/le-cabinet (3 stars, last pushed 15d ago), licensed MIT. It adds 1,466 tokens to every session, about $0.0073 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens