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 agentmods add skills/cedrickchee/text-to-cad/urdfnpx skills add cedrickchee/text-to-cad --skill urdfgit clone --depth 1 https://github.com/cedrickchee/text-to-cadWrote 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/cedrickchee/text-to-cad/urdf)<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="Measured on agentmods" 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 | $0.00114 | $0.00732 |
| Opus 5 | $0.00057 | $0.00366 |
| Sonnet 5 | $0.00023 | $0.00146 |
| Haiku 4.5 | $0.00011 | $0.00073 |
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 6d 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 — 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.urdffile as generated. - For the
gen_urdf()envelope contract, readreferences/generator-contract.md. - For robot description edits, read
references/urdf-workflow.md. - Prioritize complete physical links: include
inertial,visual, andcollisionfor 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
--summaryfor 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
.urdfentries, 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.
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.
- agents/openai.yaml 305 B
- LICENSE 1.0 KB
- references/gen-urdf.md 601 B
- references/generator-contract.md 1.3 KB
- references/urdf-workflow.md 4.2 KB
- references/validation.md 1.9 KB
- requirements.txt 9 B
- scripts/gen_urdf/cli.py 6.4 KB runs code
- scripts/gen_urdf/tests/test_cli.py 3.4 KB runs code
- scripts/tests/test_urdf_source.py 12 KB runs code
- scripts/urdf_source.py 16 KB runs code
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.
- 6d ago First seen · 41 lines · 114 tokens per session scan A d984f6471bd9
urdf is a skill published in the GitHub repository cedrickchee/text-to-cad (23 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 732 once invoked, about $0.0006 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
bambu-labs
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
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.
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…
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…
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…
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…