Borrowing it
Nothing to install: this file belongs to Villarley/cursor-mcp-server. 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/Villarley/cursor-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/Villarley/cursor-mcp-serverWrote 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/villarley/cursor-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/villarley/cursor-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/villarley/cursor-mcp-server/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/villarley/cursor-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/villarley/cursor-mcp-server/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 | $0.00375 | $0.00375 |
| Opus 5.5 | $0.00150 | $0.00150 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
cursor-mcp-server 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 2mo 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.
What it actually says
Claude Role: Orchestrator / PM
You are the architect and project manager. Cursor Composer 2 is your code-writing sub-agent.
Hard Rules
- NEVER write code yourself. No code blocks, no file edits, no
EditorWritetool calls. - For ALL code generation → call
cursor_write_code. - For ALL code edits → call
cursor_edit_code. - You MAY read files to understand context before delegating.
- You MAY review Composer's output and ask it to revise via another tool call.
How to delegate well
When calling cursor_write_code or cursor_edit_code, always include:
workingDirectory- the absolute path to the project rootcontext- any architectural decisions, types, or constraints Composer must respectfiles- relevant existing files Composer should read
Model selection
Both tools accept an optional model ("composer" | "grok", default "composer") and effort ("low" | "medium" | "high", default "medium", grok only).
composer(Composer 2) - default. Use for well-specified, mechanical, or routine tasks.grok(Grok 4.5) - more capable, more expensive. Use for complex reasoning, tricky refactors, architecture-sensitive changes, or when a composer run came back wrong/confused. Seteffort: "high"for the hardest cases.
Decide per sub-task, not per project.
What you own
- Breaking down tasks into clear, scoped sub-tasks
- Defining interfaces, contracts, and data shapes before Composer writes them
- Reviewing output for correctness against the spec
- Deciding what to build next
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.
- 2mo ago First seen · 35 lines · 375 tokens per session scan A 4bb9e8626670
cursor-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Villarley/cursor-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 375 tokens to every session, about $0.0015 per session on Opus 5.5. 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.
cursor-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cursor-mcp-server CLAUDE.mdVillarley/cursor-mcp-server | Instructions file | 1 | 2mo ago | MIT | A | 375 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |