Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Leehyunbin0131/claude-ros2-skills --skill ros2-microrosgit 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/skills/leehyunbin0131/claude-ros2-skills/ros2-microros)<a href="https://agentmods.dev/skills/leehyunbin0131/claude-ros2-skills/ros2-microros"><img src="https://agentmods.dev/badge/skills/leehyunbin0131/claude-ros2-skills/ros2-microros/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/skills/leehyunbin0131/claude-ros2-skills/ros2-microros"><img src="https://agentmods.dev/badge/skills/leehyunbin0131/claude-ros2-skills/ros2-microros.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 | $0.00029 | $0.00931 |
| Opus 5 | $0.00015 | $0.00465 |
| Sonnet 5 | $0.00006 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
ros2-microros 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
micro-ROS Instructions (Ubuntu 24.04 LTS & ROS 2 Jazzy)
Unverified. Every other domain skill in this pack was measured against a baseline agent and deleted when the agent reached the same result without it. This one has no ladder — running it needs an MCU and an agent connection that are not available here — so it survives untested, not because it earned a place. Treat its contents as a starting point to check, not as ground truth.
1. Architecture
micro-ROS connects constrained MCUs (STM32, ESP32, FreeRTOS, Zephyr) to the ROS 2 DDS graph via micro_ros_agent + the rclc client library over Micro XRCE-DDS. Static memory pools (rmw_microxrcedds) give zero steady-state heap allocation when RMW_UXRCE_ALLOW_DYNAMIC_ALLOCATIONS=OFF.
2. Documentation Entry Points
| For | Entry point |
|---|---|
| Tutorials, supported boards, transports | https://micro.ros.org/ |
Firmware build system (micro_ros_setup) |
https://github.com/micro-ROS/micro_ros_setup |
rclc executor / node API source |
https://github.com/ros2/rclc |
3. Key Concepts & Patterns
A. Embedded Client Node Setup (rclc in C)
#include <rcl/rcl.h>
#include <rclc/rclc.h>
#include <rclc/executor.h>
#include <std_msgs/msg/int32.h>
int main(void) {
rcl_allocator_t allocator = rcl_get_default_allocator();
rclc_support_t support = {0};
rcl_node_t node = {0};
rcl_publisher_t pub = {0};
rclc_support_init(&support, 0, NULL, &allocator);
rclc_node_init_default(&node, "mcu_node", "", &support);
rclc_publisher_init_default(&pub, &node, ROSIDL_GET_MSG_TYPE_SUPPORT(std_msgs, msg, Int32), "chatter");
// Clean up
rcl_publisher_fini(&pub, &node);
rcl_node_fini(&node);
rclc_support_fini(&support);
return 0;
}
B. Micro-ROS Agent Execution
# Serial Transport (e.g. UART to USB)
ros2 run micro_ros_agent micro_ros_agent serial --dev /dev/ttyUSB0 -b 115200
# UDP Transport
ros2 run micro_ros_agent micro_ros_agent udp4 --port 8888
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.
- 12d ago First seen · 72 lines · 29 tokens per session scan A 6e7dcbcd056c
ros2-microros is a skill published in the GitHub repository Leehyunbin0131/claude-ros2-skills (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 931 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
bulwark-brainstorm
Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.
plan-creation
Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
continuous-feedback
Identifies improvement targets from accumulated session learnings and proposes concrete skill/agent modifications. General-purpose pipeline for any Claude Code project.