text-to-cad: Skill for Codex

.agents/skills/robot-motion/SKILL.md

robot-motion is a skill for Codex from cedrickchee/text-to-cad. It costs 87 tokens per session (1,106 once invoked), scanned A, original, MIT.

A skill for setting up and checking robot motion from a URDF, a standard text file that describes a robot’s links and joints. It supports inverse kinematics, which calculates joint positions for a desired tool position, and path planning.

In plain words
What is it for?
Use it to install or verify ROS 2 and MoveIt 2 dependencies, generate motion artifacts, run the motion server, test its WebSocket interface, and prepare motion-enabled URDF entries for CAD Explorer.
Why use it?
It provides a defined process for generating motion files, checking the local motion service, and testing robot-motion behavior. This reduces setup and debugging work when a valid robot description already exists.

Skill for Codex

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

This is cedrickchee/text-to-cad's own configuration. It tells Codex how to work on text-to-cad 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 text-to-cad configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is PYTHONPATH=.agents/skills/robot-motion/server ./.venv/bin/python -m unittest discover .agents/skills/robot-motion/server/tests.

Reuse

Borrowing it

Nothing to install: this file belongs to cedrickchee/text-to-cad. 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/cedrickchee/text-to-cad/main/.agents/skills/robot-motion/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cedrickchee/text-to-cad

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 robot-motion

README.md
[![agentmods](https://agentmods.dev/badge/skills/cedrickchee/text-to-cad/robot-motion.svg)](https://agentmods.dev/skills/cedrickchee/text-to-cad/robot-motion)
Your own site
<a href="https://agentmods.dev/skills/cedrickchee/text-to-cad/robot-motion"><img src="https://agentmods.dev/badge/skills/cedrickchee/text-to-cad/robot-motion.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,106 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 $0.00087 $0.01106
Opus 5 $0.00044 $0.00553
Sonnet 5 $0.00017 $0.00221
Haiku 4.5 $0.00009 $0.00111

Measured 8d ago against content hash 715450f5f2cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

robot-motion 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 8d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (scripts/check-motion-server.sh, scripts/conda-common.sh, scripts/gen_motion_artifacts/cli.py, …), 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/robot-motion/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robot Motion

Use this skill after a robot URDF exists and the task needs local motion behavior: IK, path planning, MoveIt configuration, websocket motion-server debugging, or ROS dependency setup. Any valid repo-local .urdf can be used when gen_motion() names links, joints, frames, and end effectors that exist in that file.

Workflow

  1. Start from an existing valid .urdf.
  2. Generate motion artifacts from a Python source with zero-arg gen_motion() using scripts/gen_motion_artifacts/cli.py.
  3. Verify the local motion environment with scripts/check-motion-server.sh when it may already exist; run scripts/setup.sh only when dependencies are missing or stale.
  4. Run the websocket motion server with scripts/run-motion-server.sh.
  5. Test protocol, artifact generation, and provider logic before handing off motion behavior.
  6. For CAD Explorer handoff of motion-enabled .urdf entries, defer to the CAD skill and keep motion-specific metadata here.

CAD Explorer Handoff

Read .agents/skills/cad/SKILL.md, then only load its references/rendering-and-explorer.md when a task needs an Explorer URL. If unavailable, use cad-skill. Do not duplicate Explorer startup or URL syntax in this skill. Link the repo-local .urdf when motion artifacts or URDF targets were generated or changed, or when the user asks for browser review. Keep motion-specific Explorer metadata and motion-server behavior here.

Commands

Run from the robot project repository root. If the current working directory is somewhere else, set ROBOT_MOTION_REPO_ROOT to the robot project root.

python .agents/skills/robot-motion/scripts/gen_motion_artifacts/cli.py <robot-urdf-source.py> --summary
.agents/skills/robot-motion/scripts/setup.sh
.agents/skills/robot-motion/scripts/check-motion-server.sh
.agents/skills/robot-motion/scripts/run-motion-server.sh

The runtime is host-agnostic but Conda/RoboStack/Jazzy-based. The setup script creates or updates the dedicated conda environment from environment.yml, installs server/ in editable mode, and runs motion_server --check. Use any conda-compatible installation available through ROBOT_MOTION_CONDA_EXE, CONDA_EXE, PATH, or a common Miniforge/Miniconda/Anaconda install root. Do not install ROS or MoveIt packages into the repo CAD .venv, system Python, or system package managers.

Read the full file on GitHub · 71 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. 8d ago First seen · 71 lines · 87 tokens per session scan A 715450f5f2cd

Subscribe to this mod's changes

robot-motion is a skill published in the GitHub repository cedrickchee/text-to-cad (23 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 1,106 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

bambu-labs

Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

earthtojake/text-to-cad · 38 tokens

cad-viewer

Start CAD Viewer and return review links for CAD and robot-description files. Use when visually reviewing .step, .stp, .glb, .stl, .3mf, .dxf, .urdf, .srdf, or .sdf files, especially when handed off from CAD, URDF, SRDF, or SDF generation skills.

earthtojake/text-to-cad · 79 tokens

srdf

MoveIt2 SRDF authoring, validation, and planning-semantics workflow. Use when creating, editing, inspecting, or validating .srdf files, MoveIt planning groups, virtual joints, passive joints, end effectors, group states, disabled collisions, URDF-paired planning semantics, or SRDF handoff for live review. Use the URDF…

earthtojake/text-to-cad · 103 tokens

urdf

URDF robot description authoring and validation. Use when creating, editing, inspecting, validating, or debugging .urdf files, robot links, joints, limits, inertials, visual/collision geometry, mesh references, frame conventions, or robot-description artifacts. Use the SRDF skill for MoveIt2 semantic groups and…

earthtojake/text-to-cad · 92 tokens

gcode

Generate, inspect, dry-run, and statically validate plain FDM .gcode from 3D mesh files by orchestrating real slicer CLIs. Use when Codex needs to slice .stl, .obj, unsliced .3mf, .ply, .glb, or .gltf into printer-profiled G-code, discover local slicer backends, inspect whether a mesh is slice-ready, or validate…

earthtojake/text-to-cad · 102 tokens

step-parts

Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers, bearings, standoffs, and other catalog components. Use when Codex needs to search the hosted step.parts catalog before…

earthtojake/text-to-cad · 119 tokens