ros-mcp: Instructions file for Claude Code

CLAUDE.md

ros-mcp CLAUDE.md is an instructions file for Claude Code from jonasneves/ros-mcp. It costs 1,055 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for a ROS MCP server, a tool service for controlling and inspecting Robot Operating System projects. It documents how tools are organized, described, and made safe.

In plain words
What is it for?
Developing ROS tools, inspecting topics and nodes, sending simulator movement commands, and checking that motion commands stop safely afterward.
Why use it?
It helps agents add or use robot-control tools without confusing read-only actions with commands that move a robot or change its state.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is jonasneves/ros-mcp's own configuration. It tells Claude Code how to work on ros-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 ros-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jonasneves/ros-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/jonasneves/ros-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jonasneves/ros-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 ros-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jonasneves/ros-mcp/claude-md.svg)](https://agentmods.dev/instructions/jonasneves/ros-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jonasneves/ros-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jonasneves/ros-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,055 This file is loaded in full into every session.
When invoked 1,055 The same file — it is already loaded in full.
Security scan A 0 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 $0.01055 $0.01055
Opus 5 $0.00528 $0.00528
Sonnet 5 $0.00211 $0.00211
Haiku 4.5 $0.00105 $0.00105

Measured 8d ago against content hash a6d1080220cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ros-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 8d 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.

CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROS MCP Server

Commands

  • Run server: uv run server.py
  • Add to Claude (local): make configure

Architecture

Tools are registered in src/ros_mcp/tools/ and wired up in src/ros_mcp/server.py. Each tool file owns one domain (topics, services, nodes, etc.). New tools go in the relevant file and must be registered in server.py.

Tool conventions

  • readOnlyHint=True for read-only tools, destructiveHint=True for anything that publishes or mutates state
  • Tool descriptions must include units and a concrete example call
  • Motion tools must send a zero-velocity stop command as their last action
  • Use turn_by_angle / move_by_distance for rotation and straight-line motion — do not use publish_for_durations for these; it requires the caller to compute duration = angle_rad / angular_velocity and is error-prone
  • When using publish_for_durations for angular motion: duration = (angle_deg × π/180) / angular_velocity_rad_s

Simulator cmd_vel topics

The bundled setup runs 3 namespaced turtlesim instances (ts1, ts2, ts3):

Instance Topic Message type
turtlesim1 /ts1/turtle1/cmd_vel geometry_msgs/Twist
turtlesim2 /ts2/turtle1/cmd_vel geometry_msgs/Twist
turtlesim3 /ts3/turtle1/cmd_vel geometry_msgs/Twist

Docker / DDS networking

All containers must use the same DDS middleware. The rosbridge container requires RMW_IMPLEMENTATION=rmw_cyclonedds_cpp in docker-compose.yml — without it, rosbridge defaults to FastDDS and cannot discover topics from the simulator containers (which use CycloneDDS via entrypoint.sh).

cyclonedds.xml is baked into images via COPY, so changes require docker compose build before --force-recreate.

Isaac Sim

Isaac Sim uses FastDDS (ROS 2 default). The turtlesim setup forces CycloneDDS on rosbridge — do not reuse that compose file for Isaac Sim.

Read the full file on GitHub · 66 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. 8d ago First seen · 66 lines · 1,055 tokens per session scan A a6d1080220cb

Subscribe to this mod's changes

ros-mcp CLAUDE.md is an instructions file published in the GitHub repository jonasneves/ros-mcp (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,055 tokens to every session, about $0.0053 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.

Related

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.

vercel/next.js · 7,296 tokens

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

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

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

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