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 instructions/pusewicz/cf-mcp/agents-mdgit clone --depth 1 https://github.com/pusewicz/cf-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/instructions/pusewicz/cf-mcp/agents-md)<a href="https://agentmods.dev/instructions/pusewicz/cf-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pusewicz/cf-mcp/agents-md.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 5.1 | $0.01361 | $0.01361 |
| Opus 5 | $0.00681 | $0.00681 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
cf-mcp AGENTS.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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
CF::MCP is a Ruby gem that implements an MCP (Model Context Protocol) server for the Cute Framework, a C/C++ 2D game framework. It indexes header files, extracts documentation from comments, and provides search functionality for functions, structs, and enums.
Commands
# Install dependencies
bin/setup
# Run all tests
rake test
# Run a single test file
ruby -Ilib:test test/cf/mcp/parser_test.rb
# Run a specific test method
ruby -Ilib:test test/cf/mcp/parser_test.rb --name test_parse_function_doc
# Lint code with Standard Ruby
rake standard
# Auto-fix linting issues
rake standard:fix
# Run tests, lint, and generate manifest (default task)
rake
# Start interactive console
bin/console
# Install gem locally
bundle exec rake install
# Create git tag for current version
rake tag
# Create tag and push to origin
rake release:tag
# Release to RubyGems (creates tag, builds gem, pushes)
rake release
CLI Usage
# STDIO mode (for Claude Desktop integration)
cf-mcp stdio --root ~/Work/GitHub/pusewicz/cute_framework
# HTTP mode (web UI at /, MCP endpoint at /http, port 9292)
cf-mcp http --port 9292 --root /path/to/cute_framework
# Download headers from GitHub automatically
cf-mcp stdio --download
Architecture
lib/cf/mcp/
├── cli.rb # CLI with stdio/http modes
├── server.rb # MCP server setup, Server and HTTPServer classes
├── parser.rb # Header file parser (extracts @function, @struct, @enum docs)
├── index.rb # In-memory search index with relevance scoring
├── downloader.rb # GitHub header downloader with ZIP extraction
├── models/
│ ├── doc_item.rb # Base model with search/relevance scoring
│ ├── function_doc.rb # FunctionDoc with signature, params, return
│ ├── struct_doc.rb # StructDoc with members
│ └── enum_doc.rb # EnumDoc with entries
├── tools/
│ ├── search_tool.rb # search - search all types with optional type/category filters
│ ├── list_category.rb # list_category
│ └── get_details.rb # get_details - full docs by name
└── templates/ # Web UI for HTTP mode
├── index.erb
├── style.css
└── script.js
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.
- 5d ago First seen · 157 lines · 1,361 tokens per session scan A 494564321748
cf-mcp AGENTS.md is an instructions file published in the GitHub repository pusewicz/cf-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,361 tokens to every session, about $0.0068 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 instructions, from other repositories
world-intel-mcp CLAUDE.md
Claude Code instructions for marc-shade/world-intel-mcp, covering claude.md, what this is, commands, install and run mcp server (stdio mode).
autotask-mcp AGENTS.md
AGENTS.md instructions for WYRE-AI/autotask-mcp, covering task master ai - agent integration guide, essential commands, core workflow commands, project setup and daily development workflow.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
sui-mcp CLAUDE.md
Claude Code instructions for 0xfreak0/sui-mcp, covering sui-mcp, stack, architecture, which transport to use and archive fallback.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.
datadog-mcp CLAUDE.md
Claude Code instructions for dreamiurg/datadog-mcp, covering agent instructions, project, stack, commands and releases.