Borrowing it
Nothing to install: this file belongs to SocialGouv/egapro. 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/SocialGouv/egapro/alpha/CLAUDE.mdgit clone --depth 1 https://github.com/SocialGouv/egaproWrote 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/instructions/socialgouv/egapro/claude-md)<a href="https://agentmods.dev/instructions/socialgouv/egapro/claude-md"><img src="https://agentmods.dev/badge/instructions/socialgouv/egapro/claude-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.
<a href="https://agentmods.dev/instructions/socialgouv/egapro/claude-md"><img src="https://agentmods.dev/badge/instructions/socialgouv/egapro/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02295 | $0.02295 |
| Opus 5.5 | $0.00918 | $0.00918 |
| Sonnet 5.5 | $0.00459 | $0.00459 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade B, and why
egapro CLAUDE.md scanned grade B with 1 finding 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 14d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Rien à lancer : les hooks tournent seuls (`block-bad-patterns` avant chaque édition, `auto-lint` après, `check-ultra11y-plugin` au premier prompt), et les 4 gates qualité sont dus avant de déclarer une tâche terminée. Dé How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Monorepo egapro
Référence pour tout agent ou développeur travaillant sur ce dépôt.
Contexte métier
EGAPRO est la plateforme de l'État pour la déclaration de l'index d'égalité professionnelle (7 indicateurs, détaillés dans README.md).
- Indicateurs A–F : pré-calculés par le GIP-MDS depuis les données DSN, disponibles chaque mars
- Indicateur G : écart de rémunération calculé par l'entreprise par catégorie d'emploi (rémunération de base + variable)
- Seuil d'alerte : un écart ≥ 5 % déclenche des obligations supplémentaires (seconde déclaration, avis du CSE, évaluation conjointe)
- Avis du CSE : upload PDF, entreprises ≥ 100 salariés uniquement, jusqu'à 4 par an
- Tailles d'entreprise : < 50 (volontaire), 50–99 (triennal), ≥ 100 (annuel + CSE obligatoire)
Toutes les règles métier sont centralisées dans packages/app/src/modules/domain/ sous forme de fonctions pures. Spec complète : https://github.com/SocialGouv/egapro/wiki/Spec-V2
Structure du monorepo
egapro/
packages/
app/ <- application Next.js (tout le code actif)
api/ <- placeholder vide
.github/workflows/
Gestionnaire de paquets : pnpm workspaces (pnpm@10).
Si tu travailles dans packages/app/ ou sur un fichier qui en dépend, charge et applique packages/app/CLAUDE.md — stack, structure des modules, React/TypeScript, DSFR, formulaires, tests, variables d'environnement.
Où vivent les règles
Deux corpus, et la distinction est structurelle.
.claude/rules/ porte le produit et le code — ce qui est vrai quel que soit qui écrit, session directe comme agent de la pipeline. .claude/pipeline/ porte la mécanique d'orchestration /analyse → /implement, que seuls les skills, les agents pipeline et scripts/orchestration/ lisent. Une session de travail directe n'a aucun usage du board GitHub, du format de spec des tickets ou de la rubrique de sizing.
Une règle vit à un seul endroit. Si tu la trouves écrite deux fois, la deuxième est celle qui a déjà commencé à diverger : corrige la source et remplace la copie par un lien.
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.
- 14d ago Changed · +3 tokens per session 3df9cf35b048
- 1mo ago Changed · +44 tokens per session 4a29f1657abe
- 1mo ago First seen · 145 lines · 2,248 tokens per session scan B 49c6b2ddd51a
egapro CLAUDE.md is an instructions file published in the GitHub repository SocialGouv/egapro (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,295 tokens to every session, about $0.0092 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.