Borrowing it
Nothing to install: this file belongs to roslove44/brand-artisan. 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/roslove44/brand-artisan/main/CLAUDE.mdgit clone --depth 1 https://github.com/roslove44/brand-artisanWrote 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/roslove44/brand-artisan/claude-md)<a href="https://agentmods.dev/instructions/roslove44/brand-artisan/claude-md"><img src="https://agentmods.dev/badge/instructions/roslove44/brand-artisan/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/roslove44/brand-artisan/claude-md"><img src="https://agentmods.dev/badge/instructions/roslove44/brand-artisan/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 | $0.01598 | $0.01598 |
| Opus 5 | $0.00799 | $0.00799 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
brand-artisan CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guide Claude Code pour BrandArtisan, un outil de construction d'images de marque (façon next/og).
Principes
1. Think before coding. Expliciter les assumptions ; si doute → demander. Plusieurs interprétations → les présenter, ne pas choisir en silence. Approche plus simple dispo → le dire, push back quand justifié. Unclear → stop, nommer ce qui est flou, demander.
2. Simplicity first. Minimum de code qui résout le problème. Pas de features non demandées, pas d'abstraction pour du code single-use, pas de « flexibilité » non demandée, pas de handling d'erreurs impossibles. Si 200 lignes peuvent faire 50 → réécrire. Test : « un senior dirait que c'est overengineered ? » → simplifier.
3. Surgical changes. Toucher uniquement ce qui est nécessaire. Pas d'« amélioration » du code adjacent, des commentaires ou du formatting. Pas de refacto de ce qui n'est pas cassé. Matcher le style existant même si tu ferais autrement. Dead code non lié → le signaler, ne pas le supprimer. Orphans créés par tes changements → supprimer ; dead code préexistant → laisser. Test : chaque ligne modifiée trace directement à la requête utilisateur.
4. Goal-driven execution. Définir un critère de succès vérifiable, boucler jusqu'à validation. Add validation → écrire les tests pour inputs invalides, puis les faire passer. Fix bug → test qui reproduit, puis faire passer. Refactor X → tests verts avant ET après. Multi-step → plan bref Step → verify: check. Critères forts = autonomie ; critères faibles (« make it work ») = clarifications permanentes.
5. Qualité : tolérance zéro. Signaler immédiatement tout anti-pattern React 19+ : useEffect abusif, état dérivé inutile, state-flag relay, props drilling évitable, re-renders inutiles. Pas de « on verra plus tard ». eslint-disable = dernier recours absolu : épuiser toutes les alternatives (refacto, key prop, extraction de hook) avant ; justifier dans un commentaire si inévitable.
6. Franchise absolue. Être direct et franc sur les problèmes de code et autres que l'utilisateur présente. Pas besoin de prendre des gants ; priorité : qualité du projet.
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.
- 9d ago First seen · 68 lines · 1,598 tokens per session scan A 3a0fb175111f
brand-artisan CLAUDE.md is an instructions file published in the GitHub repository roslove44/brand-artisan (4 stars, last pushed 12d ago), licensed MIT. It adds 1,598 tokens to every session, about $0.0080 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.
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.
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.
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).
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).
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.
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.