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.
npx agentmods add rules/anshrajore/atelier-mcp/ateliergit clone --depth 1 https://github.com/anshrajore/atelier-mcpWrote 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/rules/anshrajore/atelier-mcp/atelier)<a href="https://agentmods.dev/rules/anshrajore/atelier-mcp/atelier"><img src="https://agentmods.dev/badge/rules/anshrajore/atelier-mcp/atelier.svg" alt="Measured on agentmods" 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 | $0.00534 | $0.00534 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
atelier 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cursorrules — 100% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atelier Quality Gate Adapter for Cursor Rules (.cursor/rules/atelier.mdc)
GENERATED FROM skills/atelier/SKILL.md — DO NOT EDIT DIRECTLY.
Run npm run sync-adapters to update.
You must strictly obey the Atelier post-generation quality gate rules for all code generation:
UNIVERSAL UI/UX RULES
- BASE-UI-101: All layout margins, paddings, and container gaps must strictly conform to an 8px harmonic grid (subgrid: 4px).
- BASE-UI-102: Font sizes must derive from a standardized modular scale, with negative tracking on display text (>=24px) and wide tracking on micro-labels (<=12px uppercase).
- BASE-UI-103: Body text and interactive icons must maintain a minimum contrast ratio of 4.5:1 against their rendered background (3.0:1 for text >= 24px).
- BASE-UI-104: A single screen or viewport state must contain exactly one primary high-emphasis call-to-action (CTA) or focal headline.
- BASE-UI-105: Visual surfaces must enforce a hard ceiling on decorative elements (gradients, drop shadows, decorative animations) per view to eliminate visual clutter.
UNIVERSAL BACKEND ARCHITECTURE RULES
- BASE-BE-201: Source code and configuration files must contain zero plaintext credentials, API tokens, or fallback defaults.
- BASE-BE-202: All external input boundaries (HTTP request body, query parameters, URL path parameters, webhook payloads) must parse through a typed schema validator before business logic execution.
- BASE-BE-203: Application error handlers must map exceptions to standard HTTP error codes and must never expose internal system stack traces, database schema details, or raw driver errors to clients.
- BASE-BE-204: Every branching condition, pipeline node, and asynchronous promise must resolve to an explicit terminal response, error handler, or dead-letter logger.
- BASE-BE-205: All public entry points and outgoing third-party network requests must define explicit timeout caps and rate limiting middleware.
FRAMEWORK PRESETS (Available in skills/atelier/presets/)
- Next.js + Tailwind:
skills/atelier/presets/nextjs-tailwind.md(17 gradeable rules) - n8n Workflows:
skills/atelier/presets/n8n.md(13 gradeable rules)
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.
- 4d ago First seen · 29 lines · 534 tokens per session scan A 3e6336245240
atelier is a cursor rule published in the GitHub repository anshrajore/atelier-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 534 tokens to every session, about $0.0027 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 cursor rules, from other repositories
laravel-inertia-integration
Guidelines for integrating PHP MCP SDK with Laravel and InertiaJS.
php-auth-implementation
Guidelines for implementing authentication and authorization in PHP MCP SDK.
php-transport-implementation
Guidelines for implementing transport layers in PHP MCP SDK.
php-types-validation
Guidelines for type definitions and validation in PHP MCP SDK.
php-client-implementation
Guidelines for implementing MCP clients in PHP.
php-server-implementation
Guidelines for implementing MCP servers in PHP.