chessceo-mcp: Instructions file for Claude Code

CLAUDE.md

chessceo-mcp CLAUDE.md is an instructions file for Claude Code from chessceo/chessceo-mcp. It costs 4,606 tokens per session, scanned D, original, MIT.

Project instructions for a TypeScript MCP server that connects AI hosts such as Claude Desktop, claude.ai, and ChatGPT to chess.ceo.

In plain words
What is it for?
Use them when editing tool handlers, shipping engine and strategy guides, or working on the chess.ceo MCP integration.
Why use it?
They explain the server’s layout, authentication model, safety role, and experimental status so agents change the correct layer without assuming backwards compatibility.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is chessceo/chessceo-mcp's own configuration. It tells Claude Code how to work on chessceo-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything chessceo-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/lucas/.nvm/versions/node/v22.21.1/bin/npx.

Reuse

Borrowing it

Nothing to install: this file belongs to chessceo/chessceo-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.

Copy the file
curl -O https://raw.githubusercontent.com/chessceo/chessceo-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chessceo/chessceo-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for chessceo-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chessceo/chessceo-mcp/claude-md.svg)](https://agentmods.dev/instructions/chessceo/chessceo-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chessceo/chessceo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chessceo/chessceo-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,606 This file is loaded in full into every session.
When invoked 4,606 The same file — it is already loaded in full.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04606 $0.04606
Opus 5 $0.02303 $0.02303
Sonnet 5 $0.00921 $0.00921
Haiku 4.5 $0.00461 $0.00461

Measured 2d ago against content hash 9ca07eab8dbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade D, and why

chessceo-mcp CLAUDE.md scanned grade D with 3 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

--force`, nuke the npx cache dir, wait 20s for CDN propagation, `sudo systemctl restart`, then verify both the running version (reads

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`deploy-mcp.sh` nukes `~/.npm/_npx` itself before every restart, so this trap is closed for the normal deploy flow. It's still live for anyone (including future-Claude) who restarts the unit directly without going throug

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **curl/scripts** → same as either of the above
CLAUDE.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chess.ceo MCP server

Model Context Protocol server that exposes chess.ceo to LLM hosts (Claude Desktop, claude.ai, ChatGPT). Every tool here is a thin wrapper on a chess.ceo backend endpoint; this package's job is LLM ergonomics, not business logic.

Repo layout (tool defs split out of index.ts in v0.44 — it's no longer a single monolithic file):

src/index.ts             Handlers + transport (stdio + streamable-HTTP) + auth. callToolInner's
                         switch is the source of truth for what each tool actually does.
src/tools.ts             All tool schemas (TOOLS[] — pure data, name/description/inputSchema).
src/prompts.ts           The three prep-workflow prompts (PROMPTS[]).
src/pgn/                 PGN parse/export/describe, node-id ↔ path resolution (paths.ts),
                         and the mutation primitives (mutations.ts: addLine, addMove,
                         deleteSubtree, promoteVariation, setAnnotations/Comment/Nags/Tag,
                         setCeoEval[Many]).
src/prep/                Prep-file library (list/search/read), and mutation orchestration
                         separate from raw pgn/mutations.ts primitives.
src/analysis/            auto_evaluate / deep_analyse job lifecycle (auto.ts, deep.ts),
                         file_handle.ts, response shaping.
src/courses.ts           find_position_in_courses / read_course_at_position — read-only
                         reference courses, distinct from the user's own prep files.
src/http.ts              Streamable-HTTP transport plumbing.
src/response_transforms.ts  UCI→SAN and other LLM-facing reshaping (see "Where this fits").
src/warnings.ts          Grounding/guardrail text injected into tool responses.
docs/*.md                Bundled at build time, served via read_*_guide tools + matching
                         prompts: engine-usage.md, prep-strategy.md, prep-files-guide.md,
                         pgn-authoring.md, summary-authoring.md.
docs/examples/*.pgn      Worked PGN examples (italian-fried-liver, najdorf-6-f4-white),
                         bundled the same way, referenced from pgn-authoring.md.
tools/fenfind/           Python side-tool (polyglot Zobrist index) that find_position_in_courses
                         shells out to. tools/sf_eval/ — local Stockfish eval helper.
package.json             files: ["dist","docs","README.md","tools"]. docs/ and tools/ must
                         ship or the doc tools and find_position_in_courses degrade/fallback.
Dockerfile               For Glama listing's automated safety checks (not for prod).
.claude-plugin/          Claude Code marketplace manifest, unrelated to the npm package.
CLAUDE.md                This file.

Read the full file on GitHub · 244 lines

Changes

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.

  1. 2d ago Changed · +43 lines · +1,088 tokens per session 9ca07eab8dbc
  2. 7d ago First seen · 201 lines · 3,518 tokens per session scan D f6b2743bc2f7

Subscribe to this mod's changes

chessceo-mcp CLAUDE.md is an instructions file published in the GitHub repository chessceo/chessceo-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 4,606 tokens to every session, about $0.0230 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens