atelier-studio: Instructions file for Claude Code

CLAUDE.md

atelier-studio CLAUDE.md is an instructions file for Claude Code from tofunori/atelier-studio. It costs 1,570 tokens per session, scanned A, original, MIT.

Project-specific instructions for Atelier Studio, a macOS app for chatting with several coding agents and working with scientific files and tools.

In plain words
What is it for?
Guiding changes to the app’s Rust backend, interface styling, scientific workspace, and related features.
Why use it?
They give agents the project’s required design choices, technical constraints, and implementation rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Codex; built for gbrain; mentions OpenCode.

This is tofunori/atelier-studio's own configuration. It tells Claude Code how to work on atelier-studio 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 atelier-studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tofunori/atelier-studio. 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/tofunori/atelier-studio/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tofunori/atelier-studio

Made for: Claude Code.

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 atelier-studio CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tofunori/atelier-studio/claude-md.svg)](https://agentmods.dev/instructions/tofunori/atelier-studio/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tofunori/atelier-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/tofunori/atelier-studio/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,570 This file is loaded in full into every session.
When invoked 1,570 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 $0.01570 $0.01570
Opus 5 $0.00785 $0.00785
Sonnet 5 $0.00314 $0.00314
Haiku 4.5 $0.00157 $0.00157

Measured today against content hash d3c69ed5eaa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

atelier-studio 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 today.

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.

CLAUDE.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atelier Studio — règles pour agents

App macOS Tauri 2 : chat multi-agents (CLIs claude/codex/grok/opencode/kimi via backend Rust atelier-studio-server — le sidecar chat Node est retiré, plan 065 phase A) + atelier scientifique (galerie, éditeurs, PDF, browser, terminal). Utilisateur : Thierry (MSc glaciologie).

Système de design — CONTRAIGNANT

Style sobre strict : jamais d'emojis colorés dans l'UI, icônes = SVG monochromes fins (stroke 1.3–1.5), pas de gradients décoratifs.

Toute valeur visuelle vient des tokens — ne jamais inventer de valeur locale :

  • Tailles de texte : 10 / 11 / 12 / 13 / 15 px uniquement (--fs-xs à --fs-xl si définis). Pas de 9px, 12.5px, 14.5px.
  • Poids : 400 (corps), 500 (accent léger), 600 (titres). Rien d'autre.
  • Rayons : 6px (contrôles), 10px (cartes/panneaux/menus), 999px (pilules). Rien d'autre.
  • Espacement : multiples de 4 (4/8/12/16/20/24). Paddings de panneaux : 16 ou 20.
  • Gris de texte : 4 niveaux — --fg (contenu), --fg2 (secondaire fort / --text-secondary), --muted (secondaire / --text-muted), --muted2 (éteint / --text-disabled). Ne pas multiplier les gris au-delà.
  • Profondeur : surfaces élevées (menus, popovers, modales) = fond + ombre douce (0 4px 16px rgba(0,0,0,.25) env.), pas une bordure de plus. Bordures 1px réservées aux séparateurs internes.
  • Typo : letter-spacing:-0.01em sur les titres ; font-variant-numeric:tabular-nums sur tout chiffre aligné (heures, tailles, compteurs) ; interligne 1.5 corps, 1.3 titres.
  • Motion : tout changement d'état visible transitionne en 120–150ms (opacity/transform). Jamais plus de 200ms. Respecter prefers-reduced-motion.
  • Thèmes : toute couleur passe par les variables CSS — jamais de hex en dur dans un composant (exceptions existantes : sémantique ok/warn/erreur documentée dans App.css).
  • Boutons : jamais de <button> nu hors src/components/ui/ et src/components/shadcn/ — utiliser Button (action textuelle), IconButton (icône seule) ou RowButton (rangée/chip/cellule/swatch/trigger cloné ; transmet ref et tous attributs natifs). Verrouillé par css-contract.test.ts.
  • Menus contextuels et déroulants : jamais de menu fait main. React → DropdownMenu / ContextMenu / Popover de src/components/ui/ (shadcn) ; galerie et éditeurs → la classe .menu du template (.mi pour les rangées). Modèle commun : fond --bg-pop/--card, aucune bordure, ombre --elev, rayon 10 (conteneur) / 6 (rangées), rangées 12 px poids 400, survol --bg-ctl/--card2, sélection = ✓ SVG à droite, destructif = --status-error, ouverture au clic (jamais au survol), 120-150 ms. Verrouillé par css-contract.test.ts (motifs *menu*, *pop*, *dropdown*) et gallery/server/tests/theme_contract.test.mjs.
  • Échelles Tailwind snappées : dans src/styles/shadcn.css, --radius-sm/md→6px, --radius-lg/xl→10px, --text-xs→12px, --text-sm→13px — les classes nommées rounded-*/text-xs/sm restent donc dans le système, même dans du code généré par le CLI shadcn. Ombres d'overlay via shadow-[var(--elevation-overlay)], voile de modale via bg-[var(--scrim)] (verrouillé aussi).

Read the full file on GitHub · 46 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. today Changed · +1 lines · +203 tokens per session d3c69ed5eaa0
  2. 6d ago First seen · 45 lines · 1,367 tokens per session scan A 17e90e556a2d

Subscribe to this mod's changes

atelier-studio CLAUDE.md is an instructions file published in the GitHub repository tofunori/atelier-studio (2 stars, last pushed today), licensed MIT. It adds 1,570 tokens to every session, about $0.0078 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

runtm copilot-instructions.md

Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.

runtm-ai/runtm · 297 tokens

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 · 5,182 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