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/lazylagom/context-compose-mcp/project-overviewgit clone --depth 1 https://github.com/lazylagom/context-compose-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/lazylagom/context-compose-mcp/project-overview)<a href="https://agentmods.dev/rules/lazylagom/context-compose-mcp/project-overview"><img src="https://agentmods.dev/badge/rules/lazylagom/context-compose-mcp/project-overview.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 | $0.00000 | $0.00407 |
| Opus 5 | $0.00000 | $0.00204 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
project-overview 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 3d 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
Context Compose Project Overview
This project is Context Compose, a TypeScript-based package that provides Model Context Protocol (MCP) server and CLI tools. This tool is for AI-assisted development context management, so I want to ensure the assets contribute meaningfully to the project's purpose. I'll need to carefully analyze each file's role to determine its necessity.
Project Structure
- Main Entry Points: Dual entry point structure defined in package.json
- CLI Tool:
context-compose- starts from src/cli/index.ts - MCP Server:
context-compose-mcp- starts from mcp-server/server.ts - Build Configuration: tsconfig.json and eslint.config.js
- Testing: vitest.config.ts and playwright.config.ts
Core Features
- MCP Server: Direct integration with AI models (Claude, ChatGPT, etc.)
- CLI Tool: Context management and workflow execution from terminal
- Context System: Project-specific development guidelines and rules management
- Workflow Engine: Automated task flows for development, testing, deployment
- Role-based Development: Apply expert personas like Dan Abramov, Martin Fowler
- Notification System: Work status notifications via Slack, email, and other channels
Key Dependencies
- fastmcp: MCP server implementation
- commander: CLI interface
- inquirer: Interactive prompts
- mustache: Template engine
- yaml: YAML file processing
- zod: Schema validation
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.
- 3d ago First seen · 35 lines · 0 tokens per session scan A 289b3fd2d91e
project-overview is a cursor rule published in the GitHub repository lazylagom/context-compose-mcp (1 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 407 tokens. 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
tools
MCP tool development patterns — factory pattern, base class, callbacks, and descriptions.
session-distill
How to distill a long work session into ContextForge so a fresh session can resume cleanly. Invoke when the user asks to distill/hand off/checkpoint the session, when context is getting bloated and work is unfinished, or before deliberately starting a new session on the same task.
user-context
用户信息 — 关于你服务的主人.
chrono-mcp-standards
Chrono MCP Project Standards and Guidelines.
ai-assisted-development
AI-Assisted Development: prompt structure, context management, iterative refinement.
cpp
C++: modern patterns, memory safety, RAII.