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/arjshiv/localutils-mcp-server/mcp-docsgit clone --depth 1 https://github.com/arjshiv/localutils-mcp-serverWhat 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 | $0.00002 | $0.00461 |
| Opus 5 | $0.00001 | $0.00230 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
mcp-docs 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 2d 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
MCP Documentation Standards
Required Documentation Components
1. Workflow Diagrams
Every MCP implementation must include Mermaid diagrams for:
- Main protocol workflow
- Error handling flow
- Data processing pipeline
- Command execution sequence
Example workflow:
graph TD
A[Start] --> B{Protocol Type}
B -->|Command| C[Execute Command]
B -->|Query| D[Process Query]
B -->|Event| E[Handle Event]
C --> F[Return Result]
D --> F
E --> F
F --> G[End]
2. Protocol Documentation
- Protocol name and version
- Request/Response schema
- Supported commands
- Error codes and handling
- Example usage
3. Implementation Details
Each implementation must document:
- Dependencies and requirements
- Configuration options
- Security considerations
- Performance characteristics
- Rate limiting (if applicable)
4. Testing Requirements
Document test coverage for:
graph LR
A[Unit Tests] --> D[Coverage]
B[Integration Tests] --> D
C[E2E Tests] --> D
D{80% Min Coverage}
File Organization
README.md Structure
protocol-name/
├── README.md
├── WORKFLOW.md
├── SECURITY.md
└── examples/
└── basic-usage.md
Style Guidelines
Mermaid Diagrams
- Use consistent node shapes
- Include color coding for different types
- Add descriptive labels
- Keep diagrams focused and clear
Code Examples
- Include TypeScript types
- Show error handling
- Provide complete working examples
- Include comments for complex logic
Review Checklist
- All required diagrams present
- Diagrams follow style guidelines
- Documentation is complete
- Examples are tested and working
- Security considerations documented
- Performance characteristics documented
Maintenance
- Update diagrams when workflow changes
- Keep examples up to date
- Review and update security docs
- Maintain test coverage documentation
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.
- 2d ago First seen · 93 lines · 2 tokens per session scan A d1bf3099c59e
mcp-docs is a cursor rule published in the GitHub repository arjshiv/localutils-mcp-server (2 stars, last pushed 8mo ago), licensed MIT. It adds 2 tokens to every session and 461 once invoked, about $0.0000 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
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
moyu
当检测到过度工程模式时自动激活:修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.
cursorrules
AgentAnycast is a decentralized P2P runtime for the A2A (Agent-to-Agent) protocol.
homunculus
Homunculus self-evolving AI assistant. Use when user asks about evolution cycles, goal trees, system status, instincts, or skills. Provides routing to detailed evolution workflows.