Borrowing it
Nothing to install: this file belongs to KevinInoCol/coppeliasim-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/KevinInoCol/coppeliasim-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/KevinInoCol/coppeliasim-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/kevininocol/coppeliasim-mcp/claude-md)<a href="https://agentmods.dev/instructions/kevininocol/coppeliasim-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kevininocol/coppeliasim-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/kevininocol/coppeliasim-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kevininocol/coppeliasim-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 | $0.01674 | $0.01674 |
| Opus 5 | $0.00837 | $0.00837 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
coppeliasim-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coppeliasim-mcp
MCP server that drives a running CoppeliaSim 4.10 over the ZMQ remote API.
Single source file: src/coppeliasim_mcp/server.py.
If you are using this server rather than developing it, you do not need this
file: the server sends its own usage guidance to the client at handshake (the
INSTRUCCIONES constant), and the user-facing detail is in README.md.
Development loop
The server is meant to be installed editable, so edits are live with no publish step in between:
pip install -e .
Point your MCP client at the coppeliasim-mcp executable that this puts in the
environment's bin/. Restart the client (or /reload-plugins) to pick up a
change; nothing else is needed.
Check your work without CoppeliaSim running:
python scripts/prueba_humo.py "$(which coppeliasim-mcp)"
That covers the MCP handshake, the expected tool count, and the one failure
mode that keeps coming back: a call with no simulator present must answer
with an actionable error instead of hanging. TOOLS_ESPERADAS in that script
is a hard count — adding a tool means updating it, which is deliberate.
Releasing
Publishing is irreversible. A PyPI version can never be overwritten or reused.
# 1. bump `version` in pyproject.toml <- the step people forget
# 2. commit and push
git tag -a vX.Y.Z -m "..." && git push origin vX.Y.Z
The tag is what publishes; a plain push never does. CI refuses to publish when
the tag and pyproject.toml disagree, and it re-runs the smoke test against
the built wheel on Python 3.10 and 3.13 before uploading. Authentication is
Trusted Publishing over OIDC, so there is no token in the repository secrets.
Semver as applied here: new tools bump the minor, fixes bump the patch.
Invariants — do not break these
- No arbitrary Lua execution, ever. This is the reason this server exists
rather than one of the others. CoppeliaSim's Lua reaches
osandio, so a Lua tool turns text inside any third-party.tttinto command execution on the user's machine. Requests to "just add anevaltool" are the threat, not a shortcut. - Paths stay confined.
cargar_escenaandguardar_escenaresolve the path before comparing it againstDIRECTORIO_ESCENAS, so../../and symlinks cannot escape.cargar_modelois limited to the local CoppeliaSim library because a.ttmcan carry Lua child scripts that run on Play. COPPELIA_MODO_LECTURA=1must disable every mutating tool. A new write tool has to honour it.- One reused ZMQ connection, not a socket per call.
pyproject.tomlis the version's source of truth.__version__and the MCP handshake both read it from package metadata, so never hardcode it there. The one unavoidable duplicate is.claude-plugin/plugin.json, which cannot read Python metadata; CI fails the release if the two disagree, because a staleplugin.jsonsilently stops users from receiving the new version.
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.
- 11d ago First seen · 142 lines · 1,674 tokens per session scan A e0580da00562
coppeliasim-mcp CLAUDE.md is an instructions file published in the GitHub repository KevinInoCol/coppeliasim-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 1,674 tokens to every session, about $0.0084 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
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.
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).
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.
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).