Borrowing it
Nothing to install: this file belongs to freeplayai/freeplay-mcp. 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/freeplayai/freeplay-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/freeplayai/freeplay-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/freeplayai/freeplay-mcp/claude-md)<a href="https://agentmods.dev/instructions/freeplayai/freeplay-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/freeplayai/freeplay-mcp/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/freeplayai/freeplay-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/freeplayai/freeplay-mcp/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 | $0.01513 | $0.01513 |
| Opus 5 | $0.00757 | $0.00757 |
| Sonnet 5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
freeplay-mcp 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 10d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Guidance for AI assistants working with this codebase
This codebase is for a Freeplay MCP server.
Project Structure
freeplay-mcp/
├── pyproject.toml
├── src/freeplay_mcp/
│ ├── api_client.py # Shared API client setup, lazy initialization, helpers
│ ├── server.py # MCP server entry point, registers tools from TOOLS list
│ ├── response.py # Utilities/Models for MCP tool responses
│ ├── secrets.py # Utilities to help obscure things such as API keys
│ ├── tools/ # One file per tool or tool group
│ │ ├── __init__.py # Exports all tool functions
│ │ ├── projects.py
│ │ ├── completions.py
│ │ └── ...
│ └── vendor/ # Vendored dependencies
│ └── swagger_client/ # Auto-generated API client
├── main.py
├── Dockerfile
└── README.md
Core Philosophy: Simplicity First
- Never add obvious comments or docstrings, prefer clarity through good naming. An exception is for the tool definitions. These should be concise but clear and written for an LLM who does not have context on the whole system.
- Use early returns/guard statements over nested if statements
- Let exceptions bubble up. Don't do catch-all error handling.
- Always prefer fewer lines of code
- Do not type ignore to resolve issues - get the types right and fix the problem
- Do not use
Any(in python) orany(ts) unless it's already in use for a value
Key Development Practices
- Respond in plaintext: MCP results will be read by an LLM, so we should return clearly structured text responses.
- Do not print: Stdio is used for returning a response. It is critical to avoid print statements other than for a response.
Safety Classification System
All operations must be classified by risk level with appropriate safeguards:
Level 0: Read (Unrestricted)
- No confirmation needed
- Cannot modify any state
- Only operations that do not require agent confirmation
- Examples: search, list, get, analyze
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.
- 10d ago First seen · 141 lines · 1,513 tokens per session scan A 2c64742f4207
freeplay-mcp CLAUDE.md is an instructions file published in the GitHub repository freeplayai/freeplay-mcp (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,513 tokens to every session, about $0.0076 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.