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/jonradoff/chessmata/claude-mdgit clone --depth 1 https://github.com/jonradoff/chessmataWrote 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/jonradoff/chessmata/claude-md)<a href="https://agentmods.dev/instructions/jonradoff/chessmata/claude-md"><img src="https://agentmods.dev/badge/instructions/jonradoff/chessmata/claude-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 | $0.04353 | $0.04353 |
| Opus 5 | $0.02176 | $0.02176 |
| Sonnet 5 | $0.00871 | $0.00871 |
| Haiku 4.5 | $0.00435 | $0.00435 |
Grade A, and why
chessmata 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 4d 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chessmata
Chessmata is a multiplayer chess platform for humans and AI agents. Play chess in a 3D browser, from the terminal, or build agents that compete via the API.
Live server: https://chessmata.metavert.io Alt URL: https://chessmata.fly.dev
Important Guidelines for Claude Code
- Always use the MCP tools (listed below) when the user asks about chess games, leaderboards, players, or anything involving Chessmata game data. Do NOT attempt to connect to MongoDB, read database files, or work around the server architecture. The MCP tools communicate with the Chessmata REST API.
- Assume the public server. Most users are connecting to
chessmata.metavert.io. They don't run their own backend. Only the project maintainer runs the full stack. - Ask before installing. When a user wants to set up Chessmata, ask whether they want to: (a) use the CLI/MCP tools to play games and build agents (client-only), or (b) install the full web application with frontend and backend. Most users want option (a).
- Don't modify server code casually. The backend and frontend are a deployed production system. Changes require
fly deployto go live. - Rebuild docs when the API changes. When API endpoints are added or modified, update all three documentation files: the HTML API reference (
backend/internal/handlers/docs.go), the markdown API reference (public/api-reference.md), and the agent skill file (public/skill.md). Keep them in sync.
Example User Prompts
These are the kinds of things users (or Claude Code itself) might ask. Use the appropriate MCP tool for each:
| Prompt | MCP Tool(s) |
|---|---|
| "What games are happening right now?" | list_active_games |
| "Show me the leaderboard" | get_leaderboard |
| "Look up the player FooBar" | lookup_user |
| "What's the current position in game abc123?" | get_game |
| "Show me the moves from that game" | get_moves |
| "Create a new game for me" | create_game |
| "Join game abc123" | join_game |
| "Play e2 to e4" / "Move my knight to f3" | make_move (convert to from/to algebraic) |
| "I resign" | resign_game |
| "Offer a draw" | offer_draw |
| "What's BeamJon's game history?" | lookup_user then get_user_game_history |
| "Find me an opponent" | join_matchmaking (generate a UUID for connection_id) |
| "Who are the top AI agents?" | get_leaderboard with type "agents" |
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.
- 4d ago First seen · 445 lines · 4,353 tokens per session scan A ef9b27142ced
chessmata CLAUDE.md is an instructions file published in the GitHub repository jonradoff/chessmata (18 stars, last pushed 5mo ago), licensed MIT. It adds 4,353 tokens to every session, about $0.0218 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 2026-08-30.
Other instructions, from other repositories
html-anything AGENTS.md
AGENTS.md instructions for nexu-io/html-anything, covering this is not the next.js you know, workspace shape and commands.
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
platform CLAUDE.md
Claude Code instructions for ambient-code/platform, covering ambient code platform, structure, key files, session flow and commands.
autogen copilot-instructions.md
Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).
toh-framework CLAUDE.md
Claude Code instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.