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 ros-claw/rosclaw --skill rosclaw-embodiedgit clone --depth 1 https://github.com/ros-claw/rosclawWrote 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/ros-claw/rosclaw/rosclaw-embodied)<a href="https://agentmods.dev/skills/ros-claw/rosclaw/rosclaw-embodied"><img src="https://agentmods.dev/badge/skills/ros-claw/rosclaw/rosclaw-embodied/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/ros-claw/rosclaw/rosclaw-embodied"><img src="https://agentmods.dev/badge/skills/ros-claw/rosclaw/rosclaw-embodied.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00677 |
| Opus 5.5 | $0.00022 | $0.00271 |
| Sonnet 5.5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
rosclaw-embodied 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.
What it actually says
ROSClaw 具身任务纪律
Pi 是唯一大脑：理解用户目标、调查环境、组合通用原语、没有现成 能力时在任务沙箱写代码、运行观察修错、判断是否完成用户目标。
通用物理原语（SIM 自动执行，不弹批准）
trajectory_generate_planar_path：任意路径点 waypoints[{x,y,z,contact?}]（contact=false=抬笔移动段）——文字/任意 图形都由你表达为点列；shape=star5|circle 只是便捷参数， 没有默认形状。返回 plan_id 句柄。ur5e_simulate_cartesian_trajectory(plan_id)→ trace_id （真实 MuJoCo 动力学 rollout + 跟踪指标）。simulation_verify_tracking(trace_id, max_tracking_error_m)→ 诚实 PASS/FAIL + 误差数值。simulation_render_trace(trace_id, format=gif)/simulation_render_scene(trace_id, camera=...)→ 交付物。- 观测：
ur5e.get_end_effector_pose等 OBSERVE 面。 - 可信上下文每轮带 workspace_window（安全半径/z 窗口）—— 摆 waypoints 不要越界（规划器硬校验，越界即拒）。
任务沙箱编码
- 活跃任务的
scratch/区可写可运行（write/edit/bash cwd 限定在 session 工作区与任务 scratch 内）——写几十行 Python 把字母/ 图形转成点列是正常能力，不需要内核替你认识任何形状。 - scratch 是草稿——交付物登记走 outputs/（register_artifact）。
证据与验收
- 交付物必须登记（rosclaw_artifact_register）——口头提到不算。
- 仿真证据标 simulated——动力学自洽不证明真机效果。
- 用户否定结果后修正或重开 revision——不得拿旧结果冒充。
安全分层
- SIM：物理原语工具 + 任务沙箱代码自动执行。
- 真机动作：必须走 rosclaw_request_action 的 admission 链 （rosclawd + permit + operator），任何其他路径都不是执行权威。
- 改产品核心源码不是任务能力——走开发流程（克隆仓库+PR）。
- 同一调用同一参数失败后不机械重试；先读结构化诊断。
权威资产
- 机器人模型只认 e-URDF-Zoo 权威资产；测试 fixture 绝不出现在 交付证据里。不确定资产来源时先调查，不从 / 全盘搜索。
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 · +22 lines · +4 tokens per session a8a18b126528
- 1mo ago First seen · 30 lines · 50 tokens per session scan A 46137af04c35
rosclaw-embodied is a skill published in the GitHub repository ros-claw/rosclaw (230 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 677 once invoked, about $0.0002 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 skills, from other repositories
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
xiaoai-tts
Control Xiaoai speaker via OpenXiaoAI Voice API for high-quality TTS playback. Use when the user wants to play voice notifications, announcements, or TTS through the Xiaoai speaker using the OpenXiaoAI HTTP API. Supports Doubao (ByteDance) TTS with emotions, voice types, and speed control. Triggers on queries like…
environment
Interpret environmental sensor readings and sustained changes for room comfort and air quality. Use for [environment:initial] greeting context, [environment:update] events, questions about room temperature, humidity, measured CO2 or air quality, checking changes after ventilation or air cleaning, and room-feeling…
sensing-track
Query flow event logs to answer questions about past sensing events — "Have you seen anybody between 10pm and midnight?", "Is there any motion in the last hour?", "What happened while I was away?". Also holds your OWN sleep history — "how many times have you slept?", "when do you usually go to sleep?".
sensing
React to passive device events tagged [sensing:...] — presence, sound, light, fire hazard — with inline emotion markers and optional short speech. Does NOT handle motion.activity (→ wellbeing) or emotion.detected / speechemotion.detected (→ user-emotion-detection).