ros-mcp: Skill for Claude Code

.claude/skills/ros/SKILL.md

ros is a skill for Claude Code from jonasneves/ros-mcp. It costs 38 tokens per session (1,293 once invoked), scanned A, original, Apache-2.0.

A set of rules for writing ROS 2 robot software, including how nodes communicate and how positions and coordinates are represented. ROS 2 is a framework for building software that runs on robots and other robotic systems.

In plain words
What is it for?
Choosing ROS 2 topics, services, actions, and quality settings; defining robot coordinate frames; and writing compatible URDF robot descriptions.
Why use it?
Following these conventions helps avoid errors that may stay hidden until the robot is under load, such as dropped messages or incorrect coordinate frames.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions 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/skills/ros/SKILL.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

README.md
[![agentmods](https://agentmods.dev/badge/skills/jonasneves/ros-mcp/ros/github.svg)](https://agentmods.dev/skills/jonasneves/ros-mcp/ros)
Your own site
<a href="https://agentmods.dev/skills/jonasneves/ros-mcp/ros"><img src="https://agentmods.dev/badge/skills/jonasneves/ros-mcp/ros/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.

agentmods 80×15 button for ros

Your own site · 80×15
<a href="https://agentmods.dev/skills/jonasneves/ros-mcp/ros"><img src="https://agentmods.dev/badge/skills/jonasneves/ros-mcp/ros.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,293 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00038 $0.01293
Opus 5 $0.00019 $0.00647
Sonnet 5 $0.00008 $0.00259
Haiku 4.5 $0.00004 $0.00129

Measured 3d ago against content hash e168342968a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ros 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 3d 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/skills/ros/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROS 2

Principle: ROS 2 conventions (REPs), when violated, produce silent failures — wrong coordinate frames, dropped messages, timing bugs that only appear under load. Every deviation is a future debugging session.

Ask: does this follow the REP, or is it ad-hoc?

Coordinate conventions (REP-103)

Right-handed, SI units throughout. X forward, Y left, Z up. Units: meters, radians, seconds, kilograms — no degrees, millimeters, or custom units. Euler angles discouraged (24 valid conventions; systems default differently); use quaternions for all rotation in messages. Differs from Three.js (Y-up) and some robot hardware; document deviations in project CLAUDE.md and verify with a coordinate transform before assuming.

Frame conventions (REP-105)

Mobile-robot hierarchy: map → odom → base_link → [sensor frames].

Frame Published by Meaning
map Localization node World-fixed; corrected by localization
odom Odometry source World-fixed; continuous, no jumps, drifts over time
base_link Robot center Attached to robot body
base_footprint Optional Projection of base_link onto ground plane

Localization publishes map → odom, not map → base_link — so odom → base_link stays continuous (no jumps) and corrections go into map → odom.

TF2

Tree must be a tree: each frame exactly one parent; no loops, disconnected subtrees, or gaps.

ros2 run tf2_tools view_frames                          # visualize tree
ros2 run tf2_ros tf2_echo <source_frame> <target_frame> # check a transform

Static vs dynamic: unchanging frames (sensor on robot) → StaticTransformBroadcaster; changing frames (robot in world) → TransformBroadcaster. Dynamic-for-static wastes bandwidth; static-for-dynamic publishes stale transforms.

Transform direction: parent → child = position of child frame's origin expressed in parent frame. lookupTransform(target, source, time) returns the transform moving a point from source to target. Most common source of sign errors — verify direction before assuming.

Read the full file on GitHub · 98 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. 3d ago First seen · 98 lines · 38 tokens per session scan A e168342968a3

Subscribe to this mod's changes

ros is a skill published in the GitHub repository jonasneves/ros-mcp (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,293 once invoked, about $0.0002 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 2026-09-05.

Related

Other skills, from other repositories

robotics-expert

Develop production-ready robotic systems with autonomous navigation, sensor fusion, and intelligent control for real-world applications. Use when the user mentions ROS or ROS 2, autonomous navigation, SLAM, motion planning, sensor fusion, or robot control systems.

personamanagmentlayer/pcl · 53 tokens

exporting-visualizations

Use when the user wants to SEE robot data — visualize, plot, replay, or export a log or query result from bagel to a viewer or training format (Rerun, Lichtblick, PlotJuggler, LeRobot).

Extelligence-ai/bagel · 54 tokens

operating-live-sinks

Use when subscribing to live robot data (MQTT, rosbridge) through bagel, managing standing pipelines that survive restarts, or when questions about live-buffer sizes and disk usage come up.

Extelligence-ai/bagel · 45 tokens

triaging-robot-logs

Use when investigating a robot log or flight log with bagel — finding events, anomalies, or "what happened around X" in rosbags, MCAP, CAN, MDF4, ULog, or Betaflight files. Routes to the server's triage capability.

Extelligence-ai/bagel · 63 tokens

ros2-engineering-skills

Use for ROS 2 development, review, and debugging: rclcpp/rclpy, colcon/ament, launch, QoS/DDS, tf2/URDF, ros2control, Nav2, MoveIt 2, sensors, simulation, real-time behavior, hardware safety, runtime provenance, SROS2, micro-ROS, and multi-robot systems. Also use for ROS 1 migration to ROS 2. Do not use for general…

dbwls99706/ros2-engineering-skills · 114 tokens

ros2-skill

Use this skill for any ROS 2 robot task: topics (subscribe, publish, capture images, find by type), services (list, call), actions (list, send goals), parameters (get, set, presets), nodes, lifecycle management, controllers (ros2control), Nav2 navigation (go, rotate, cancel, costmap-clear, waypoints, move-timed…

adityakamath/ros2-skill · 148 tokens