A tool for creating and checking URDF files, which are XML descriptions of a robot’s links, joints, shapes, and movement limits.

Use it to create, edit, regenerate, inspect, or validate robot description files and their links, joints, collision shapes, and visual meshes.

It helps catch incorrect robot structure, movement limits, XML, and mesh references before a simulator or other robot software uses the model.

How cedrickchee/text-to-cad configures Codex

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/urdf/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cedrickchee/text-to-cad/urdf/github.svg)](https://agentmods.dev/skills/cedrickchee/text-to-cad/urdf)

Your own site

<a href="https://agentmods.dev/skills/cedrickchee/text-to-cad/urdf"><img src="https://agentmods.dev/badge/skills/cedrickchee/text-to-cad/urdf/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cedrickchee/text-to-cad/urdf"><img src="https://agentmods.dev/badge/skills/cedrickchee/text-to-cad/urdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 732 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.

Model	Per session	Once invoked
Fable 5.1	$0.00114	$0.00732
Opus 5.5	$0.00046	$0.00293
Sonnet 5.5	$0.00023	$0.00146
Haiku 4.5	$0.00011	$0.00073

Measured 2mo ago against content hash d984f6471bd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

urdf 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/gen_urdf/cli.py, scripts/gen_urdf/tests/test_cli.py, scripts/tests/test_urdf_source.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/urdf/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

URDF

Use this skill for robot description outputs. URDF work is intentionally separate from ordinary CAD generation because the correctness questions are kinematic, XML, and mesh-reference oriented rather than primarily geometric.

Consumer-specific metadata is allowed when a downstream UI or simulator adapter expects it. Treat that metadata as generator-owned extension data rather than standard URDF.

Defer CAD handoff details to the CAD skill: read .agents/skills/cad/SKILL.md, then only load its references/rendering-and-explorer.md when a URDF needs a CAD Explorer link. If the local CAD skill is unavailable, use cad-skill as the fallback reference. Keep URDF-specific generation and explorer_metadata contracts in this skill.

Workflow

Treat the Python source that defines gen_urdf() as source of truth. Treat the configured .urdf file as generated.
For the gen_urdf() envelope contract, read references/generator-contract.md.
For robot description edits, read references/urdf-workflow.md.
Prioritize complete physical links: include inertial, visual, and collision for each link that represents physical robot geometry. Frame-only links may intentionally omit them.
Edit links, joints, limits, axes, origins, inertials, materials, visual/collision geometry, mesh filenames, and any consumer-specific sidecar metadata deliberately.
Regenerate only the explicit URDF target with scripts/gen_urdf/cli.py.
Use --summary for a compact robot/link/joint check after regeneration.
For validation expectations, read references/validation.md.
If URDF mesh references depend on changed CAD, mesh, or render outputs, regenerate only the affected explicit targets with the owning CAD or mesh workflow.
For CAD Explorer handoff of generated .urdf entries, use the CAD skill's Explorer handoff rules rather than duplicating link syntax here.

Commands

Run with the Python environment for the project or workspace. If the environment lacks the URDF validation runtime packages, install this skill's script dependencies from requirements.txt. Invoke the tool as a filesystem script, for example python <urdf-skill>/scripts/gen_urdf/cli.py .... Relative target paths are resolved from the current working directory; the tool does not prepend a project root.

Read the full file on GitHub · 41 lines

Files

What ships with it

11 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.

2mo ago First seen · 41 lines · 114 tokens per session scan A d984f6471bd9

Subscribe to this mod's changes

urdf is a skill published in the GitHub repository cedrickchee/text-to-cad (45 stars, last pushed 6mo ago), licensed MIT. It adds 114 tokens to every session and 732 once invoked, about $0.0005 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.

Hardware and IoT ai-agents cad cad-skill mechanical-engineering robotics text-to-cad

urdf next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
urdfcedrickchee/text-to-cad	Skill	45	6mo ago	MIT	A	114	Codex
step-partsearthtojake/text-to-cad	Skill	26k	yesterday	MIT	A	126	Claude Code, Codex
gcodeearthtojake/text-to-cad	Skill	26k	yesterday	MIT	A	115	Claude Code, Codex
sendcutsendearthtojake/text-to-cad	Skill	26k	yesterday	MIT	A	75	Claude Code, Codex
srdfearthtojake/text-to-cad	Skill	26k	yesterday	MIT	C	107	Claude Code, Codex
urdfearthtojake/text-to-cad	Skill	26k	yesterday	MIT	C	110	Claude Code, Codex
dfam-checkearthtojake/text-to-cad	Skill	26k	yesterday	MIT	A	117	Claude Code, Codex

text-to-cad: Skill for Codex