A French-language project-planning assistant that asks structured questions and creates or expands docs/PRD.md. A PRD is a document describing a product’s problem, users, proposed solution, boundaries, and success measures.

Use it to define a project, write user stories, set success criteria, record implementation decisions, and note what is outside the project’s scope.

It turns an incomplete idea into a shared written plan and checks existing project documents before asking questions.

cadre — Skill for Claude Code by naiersaidane

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add naiersaidane/claude-mastery --skill cadre

Clone the repo

git clone --depth 1 https://github.com/naiersaidane/claude-mastery

Made for: Claude Code.

Or install claude-mastery, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/cadre/github.svg)](https://agentmods.dev/skills/naiersaidane/claude-mastery/cadre)

Your own site

<a href="https://agentmods.dev/skills/naiersaidane/claude-mastery/cadre"><img src="https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/cadre/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/naiersaidane/claude-mastery/cadre"><img src="https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/cadre.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 964 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket pass 15 Jun 2026
Snyk pass 15 Jun 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00154	$0.00964
Opus 5	$0.00077	$0.00482
Sonnet 5	$0.00031	$0.00193
Haiku 4.5	$0.00015	$0.00096

Measured 11d ago against content hash 85a777b1b3d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cadre 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 11d 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.

skills/cadre/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tu interroges l'utilisateur pour produire ou étendre docs/PRD.md selon le template ci-dessous.

Process

Explore le repo si nécessaire pour comprendre le contexte existant (CLAUDE.md, ADRs, glossaire métier, code adjacent). Réutilise le vocabulaire du projet dans le PRD et respecte les décisions architecturales déjà tranchées. Si la réponse à une question se trouve dans le repo, explore plutôt que de demander.
Si docs/PRD.md existe, lis-le. Croise avec le brief reçu et n'interroge que sur les deltas. Confronte les contradictions : « Tu avais tranché X, le brief suggère Y, on garde lequel ? ». Pas de PRD et pas de brief → ta première question est « Qu'est-ce que tu veux cadrer ? ».
Interroge une question à la fois, avec ta recommandation justifiée. Suis les dépendances : Problème → Utilisateur cible → Solution → Critères → Hors périmètre. User Stories et Décisions d'implémentation émergent en transverse. Avant de basculer, demande « Quelque chose pour Notes complémentaires : risques, dépendances, hypothèses ? ».
Quand chaque section peut être rédigée sans trou, annonce-le en une phrase et écris le PRD complet dans le chat selon le template. Les User Stories sont synthétisées à ce moment à partir des autres réponses et présentées à valider.
Le user valide ou corrige section par section. Sur correction, re-poste uniquement la section touchée. Une fois tout validé, écris docs/PRD.md (crée docs/ au besoin) et confirme « ✓ écrit dans docs/PRD.md ».

Problème

Ce que vit l'utilisateur : frustration, contexte, « pourquoi maintenant ». Prose en 3ème personne, pas en je.

Solution

Direction produit du point de vue de l'utilisateur : ce que le produit lui permet de faire, pas comment c'est construit.

Utilisateur cible

Profil + contexte d'usage, suffisamment précis pour imaginer une personne réelle.

User Stories

Liste numérotée exhaustive au format « En tant que <acteur>, je veux <fonctionnalité>, afin de <bénéfice> ». Couvre interactions principales, états vides, erreurs, parcours alternatifs, cas limites.

Read the full file on GitHub · 60 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.

11d ago First seen · 60 lines · 154 tokens per session scan A 85a777b1b3d8

Subscribe to this mod's changes

cadre is a skill published in the GitHub repository naiersaidane/claude-mastery (51 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 964 once invoked, about $0.0008 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.

Claude Code Planning agent-skills ai claude-skills skills-sh

geekx-gate

A review framework for deciding whether an engineering idea or technical commitment is necessary, too broad, or premature. It examines the real problem, complexity, evidence, non-goals, and ease of reversal.

geekjourneyx/geekx-skills · 155 tokens

geekx-engineering

A set of engineering instructions for making substantial changes in an existing codebase. It emphasizes understanding the affected system, keeping a persistent plan, and recording decisions and evidence.

geekjourneyx/geekx-skills · 59 tokens

geekx-grilling

A questioning workflow for pressure-testing plans, decisions, requirements, and proposed solutions. It asks one important question at a time and uses the answers to clarify facts, choices, dependencies, scope, and exclusions.

geekjourneyx/geekx-skills · 95 tokens

specmint-core

Persistent spec management for AI coding workflows. Use this skill when the user explicitly mentions specs, forging, or structured planning: says "forge", "forge a spec", "write a spec for X", "create a spec", "plan X as a spec", "resume", "what was I working on", "spec list/status/pause/switch/activate", "implement…

ngvoicu/specmint-core · 154 tokens

siti-grants

A guide to Taipei's SITI industry-development grants for companies, including funding for research, startups, branding, and related programmes. SITI is the Taipei City Government's industry-development funding office.

hunthung-code/siti-grants · 102 tokens

publisher

Publish HTML frontend projects to the PushWebly publishing platform, list published projects, obtain shareable project URLs, change a published app's public/private visibility, and package published HTML projects into Android APKs. Use when Codex needs to publish a local zip project, publish and build an APK, build an…

publisher-skill/publisher · 109 tokens