Borrowing it
Nothing to install: this file belongs to Leehyunbin0131/claude-ros2-skills. 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/Leehyunbin0131/claude-ros2-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/Leehyunbin0131/claude-ros2-skillsWrote 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/leehyunbin0131/claude-ros2-skills/claude-md)<a href="https://agentmods.dev/instructions/leehyunbin0131/claude-ros2-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/leehyunbin0131/claude-ros2-skills/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/leehyunbin0131/claude-ros2-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/leehyunbin0131/claude-ros2-skills/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 | $0.00840 | $0.00840 |
| Opus 5.5 | $0.00336 | $0.00336 |
| Sonnet 5.5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
claude-ros2-skills 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 1mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
READ THIS FIRST — ROS 2 verification protocol
This protocol guides verification for ROS 2, Gazebo, Nav2, MoveIt, ros2_control, and perception tasks on Ubuntu 24.04 LTS / ROS 2 Jazzy Jalisco.
Environment-Dependent Facts
Do not guess environment-dependent facts (such as exact message fields, parameter names, QoS profiles, topic names, and TF frames) from memory. Pretrained API details are frequently outdated or divergent between distributions.
When implementing or modifying ROS 2 code:
- Verify uncertain or distribution-specific APIs against the local installation (
/opt/ros/jazzy/viaros2 interface show,ros2 topic list -t,ros2 pkg prefix,ros2 param list) or official Jazzy documentation. General ROS concepts and established programming patterns do not require repetitive tool lookups when the API is already unambiguous. - Resolve frame and TF conventions against REP 103 and REP 105 as ground truth. Refer to
references/frames.mdlocated inside the loadedros2-troubleshootingskill directory (resolved relative to that skill's path, not the project CWD). - Diagnose silent failures with targeted checks: When nodes appear running but communication fails, run relevant troubleshooting checks (e.g., QoS compatibility). An exit code of 0 or 1 applies strictly to the checked property; code 2 indicates an inconclusive or invalid request. A diagnostic check does not establish whole-system correctness.
rclcpp is C++ only; rclpy is Python only. They are distinct libraries with different conventions and type signatures. An example in one language translates as an architectural concept, never as a literal namespace import. Use the language appropriate for the task, and verify symbol presence when uncertain.
Establish Relevant Context Before Writing
Before modifying or writing code, clarify facts relevant to the task if they are not already supplied by the user or workspace:
- Real hardware, simulation, or both? Affects
use_sim_time, physical sensor expectations, and tuning validity. - Existing workspace conventions: Follow the package layout, naming, and launch patterns already present in the workspace rather than imposing new structures.
- Existing publishers and TF authorities: Avoid creating duplicate publishers on the same topic or transform frame without coordination.
- Physical geometry: Sensor mounting orientations and wheel dimensions must reflect actual hardware, not unverified CAD assumptions.
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.
- 1mo ago Changed · +4 lines · +100 tokens per session 93df2cfb48dc
- 1mo ago Changed · +2 lines · +97 tokens per session e927346aeba4
- 1mo ago First seen · 31 lines · 643 tokens per session scan A 8c8bd05855b4
claude-ros2-skills CLAUDE.md is an instructions file published in the GitHub repository Leehyunbin0131/claude-ros2-skills (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 840 tokens to every session, about $0.0034 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.