rosclaw: Skill for Codex

.agents/skills/rosclaw-simforge/SKILL.md

rosclaw-simforge is a skill for Codex from ros-claw/rosclaw. It costs 97 tokens per session (2,398 once invoked), scanned A, original, MIT.

A workflow guide for safely setting up, checking, diagnosing, and improving ROSClaw simulations. ROSClaw is software for testing robot-control systems in simulators and related services without directly driving real hardware.

In plain words
What is it for?
Use it for smoke tests, simulator integration, ROS 2 and MCP checks, multi-GPU training validation, and ROSClaw Hub transfers.
Why use it?
It provides checks and safety boundaries for the full path from command-line tools to simulators, evidence records, and shared assets.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is ros-claw/rosclaw's own configuration. It tells Codex how to work on rosclaw 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 rosclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ros-claw/rosclaw. 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/ros-claw/rosclaw/main/.agents/skills/rosclaw-simforge/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ros-claw/rosclaw

Made for: Codex.

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 rosclaw-simforge

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ros-claw/rosclaw/rosclaw-simforge"><img src="https://agentmods.dev/badge/skills/ros-claw/rosclaw/rosclaw-simforge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,398 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00097 $0.02398
Opus 5 $0.00048 $0.01199
Sonnet 5 $0.00019 $0.00480
Haiku 4.5 $0.00010 $0.00240

Measured 9d ago against content hash 8ee5b1fe06f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rosclaw-simforge 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 9d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/verify_gazebo.sh, scripts/verify_hub.sh, scripts/verify_isaaclab.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/rosclaw-simforge/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROSClaw SimForge

Validate the full software loop from CLI and safety gates through simulators, MCP, evidence receipts, and asset distribution. Treat real hardware as out of scope unless the user separately authorizes it.

Safety boundary

  • Use the exact rosclaw CLI from the checkout's .venv/bin; report a stale global CLI before changing it.
  • Use a temporary ROSCLAW_HOME for smoke tests and Hub operations.
  • Write raw trajectories, logs, receipts, and reports to an evidence directory outside the source checkout. Commit only reproducible code and tests.
  • ROS graph discovery, subscription, and simulation are allowed. Never publish actuator commands directly, call a motion service, or send an action goal.
  • Route any action request through rosclawd request_action / ROSClaw MCP so the daemon, sandbox, and firewall remain in the path.
  • Do not stop unrelated GPU processes or containers. Inspect available memory and choose the smallest useful workload.
  • A dependency failure is a failure to diagnose and install around, not a passing skip. Keep unsupported real-robot checks explicitly out of scope.

Workflow

1. Establish provenance

Read the repository AGENTS.md and the task's verification document. Record:

git rev-parse HEAD
git status --short
nvidia-smi --query-gpu=index,name,memory.used,memory.free --format=csv

Fetch or compare upstream before claiming the checkout is current. Preserve all pre-existing user changes.

2. Validate the ROSClaw core

Prepend the repository environment to PATH, use a temporary home, and run doctor, status, the deterministic demo, receipt explanation, and the universal agent/MCP probe. Then run the repository test groups requested by the project verification document.

Do not claim a simulator pass from import-only evidence. Require a physics step, a bounded task outcome, and a receipt or other machine-readable result.

3. Validate ROS 2 and Gazebo

Run scripts/verify_ros2.sh from this skill directory. It builds the Humble rosbridge/turtlesim image, deploys the stack, discovers the live graph, subscribes to pose, and proves direct velocity requests are blocked.

Read the full file on GitHub · 207 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 207 lines · 97 tokens per session scan A 8ee5b1fe06f4

Subscribe to this mod's changes

rosclaw-simforge is a skill published in the GitHub repository ros-claw/rosclaw (196 stars, last pushed 2d ago), licensed MIT. It adds 97 tokens to every session and 2,398 once invoked, about $0.0005 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.