agentmods.dev

Dossier-Facile-Frontend: Instructions file for Codex

AGENTS.md

Dossier-Facile-Frontend AGENTS.md is an instructions file for Codex, OpenCode from MTES-MCT/Dossier-Facile-Frontend. It costs 1,083 tokens per session, scanned A, original, MIT.

A project guide for the DossierFacile frontend, a French public service that helps renters prepare verified digital rental applications. It documents the codebase, its apps, shared packages, tools, and development cautions.

In plain words
What is it for?
It helps agents work on the renter, landlord, public website, and document-watermarking apps, while following the project's Vue, TypeScript, testing, authentication, and design-system conventions.
Why use it?
It gives coding agents the project context they need before changing code, reducing mistakes in a large codebase with several web apps and shared libraries.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is MTES-MCT/Dossier-Facile-Frontend's own configuration. It tells Codex and OpenCode how to work on Dossier-Facile-Frontend 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 Dossier-Facile-Frontend configures →

not rated 86repo 4d ago A scan 1,083 tokens original MIT
View source ↗ MTES-MCT/Dossier-Facile-Frontend dossierfacile.logement.gouv.fr
Reuse

Borrowing it

Nothing to install: this file belongs to MTES-MCT/Dossier-Facile-Frontend. 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/MTES-MCT/Dossier-Facile-Frontend/develop/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/MTES-MCT/Dossier-Facile-Frontend

Made for: 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 Dossier-Facile-Frontend AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mtes-mct/dossier-facile-frontend/agents-md.svg)](https://agentmods.dev/instructions/mtes-mct/dossier-facile-frontend/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mtes-mct/dossier-facile-frontend/agents-md"><img src="https://agentmods.dev/badge/instructions/mtes-mct/dossier-facile-frontend/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,083 This file is loaded in full into every session.
When invoked 1,083 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 $0.01083 $0.01083
Opus 5 $0.00541 $0.00541
Sonnet 5 $0.00217 $0.00217
Haiku 4.5 $0.00108 $0.00108

Measured 8d ago against content hash 5260047c2f51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Dossier-Facile-Frontend 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 8d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — DossierFacile Frontend

DossierFacile.fr (service public, Ministère de la Transition écologique) aide les candidats locataires à constituer un dossier de location numérique vérifié.

Ce monorepo héberge les interfaces web de DossierFacile, ainsi que celle de FiligraneFacile (sous-produit de filigrane de documents), portée par le package watermark.

Stack technique

  • Langages / Framework : Vue 3 (Composition API), TypeScript
  • Build / Runtime / Package manager : Vite, Node 22, pnpm
  • Formulaires : vee-validate (+ règles custom déclarées dans les main.ts)
  • HTTP / auth : Axios , keycloak-js (OIDC)
  • Design system : DSFR (@gouvfr/dsfr + @gouvminint/vue-dsfr)
  • Tests : Vitest, Cypress (package e2e-tests)
  • Analytics : Matomo

Packages

Package Rôle
tenantv3 App locataire - funnel de constitution du dossier
owner App propriétaire - gestion des propriétés et candidatures
www Site vitrine
watermark App FiligraneFacile - standalone app de filigranage de document
df-shared-next Lib partagée : composants, modèles TS, services, validateurs, plugins (consent, robots, Crisp)
storybook Documentation des composants
e2e-tests Tests Cypress

Commandes depuis la racine : pnpm install, puis pnpm --filter <package> dev | build | test:unit | lint | tsc.

Backend

Repo backend : https://github.com/MTES-MCT/dossierfacile-backend Ce frontend échange avec 3 API du repo backend:

  • tenantv3 -> api-tenant
  • owner -> api-owner
  • watermark -> api-watermark Le modèle de donnée et les différents statuts du dossier sont définis dans le AGENTS.md du repo backend

Points d'attention avant tout dev

Pour limiter les risques de régressions, évaluer l'impact sur chacun de ces axes ; le traiter ou le justifier.

  • i18n : toute clé ajoutée doit être mise en priorité dans le bloc <i18n> du composant. Si c'est une traduction commune à plusieurs composants, elle est à ajouter dans le fr.json/en.json/base.json dans le /src de chaque package.
  • Design : DSFR obligatoire (RGAA). Privilégier les composants @gouvminint/vue-dsfr et ceux déjà utilisés dans la codebase. Se référer en seconde priorité à @gouvfr/dsfr. Utiliser les tokens DSFR plutôt que des valeurs en dur : classes utilitaires d'espacement (fr-mt-3w…) et variables CSS de couleur (var(--primary)…)
  • Accessibilité (RGAA) : axe prioritaire et obligation légale de viser un site "totalement conforme" au RGAA.
    • Modales : utiliser le composant DsfrModalPatch.vue (a11y compatible) plutôt que le DsfrModal de vue-dsfr
    • Titres de page : Les titres doivent décrire la hiérarchie d'information du funnel (voir le afterEach dans tenantv3/src/router/index.ts).
    • Roles : Faux positifs Sonar attendus : role="list" sur <ul> (contournement du bug VoiceOver quand list-style:none) et role="presentation" sur <li> d'une structure d'onglets — ne pas « corriger » en supprimant ces rôles.
    • Formulaires : toujours associer un input avec un label, renseigner l'attribut required sur les champs obligatoires et afficher en toute lettre leur caractère "obligatoire" ou "facultatif", renseigner aria-describedby / aria-invalid sur les champs en erreur, utiliser fieldset et legend pour les groupes de champs. Pour les erreurs multiples, afficher la listes des erreurs reliées aux champs dans un bloc dédié via le composant ErrorSummary.vue.
    • Contenu dynamique : ajouter le role="status" ou annoncer les changements via aria-live="polite".
    • Vérifier la navigation clavier et la présence du focus visible.
    • Tests E2E : Utiliser axe-core pour tester l'a11y sur le principaux scenarios

Read the full file on GitHub · 57 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. 8d ago First seen · 57 lines · 1,083 tokens per session scan A 5260047c2f51

Subscribe to this mod's changes

Dossier-Facile-Frontend AGENTS.md is an instructions file published in the GitHub repository MTES-MCT/Dossier-Facile-Frontend (86 stars, last pushed 4d ago), licensed MIT. It adds 1,083 tokens to every session, about $0.0054 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.

Frontend
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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens