kernelcad-srdf

kernelcad-srdf is a skill for Claude Code, Codex from w1ne/kernelCAD-web. It costs 50 tokens per session (744 once invoked), scanned A, original, MIT.

An exporter that adds robot-planning information to a URDF, which is a standard description of a robot's links and joints. It can describe groups of joints, grippers, virtual joints, safe collision exceptions, and named poses.

In plain words
What is it for?
Use it when a robot assembly needs named arm or gripper groups, end-effectors, pose snapshots, or collision rules for a motion-planning system.
Why use it?
It supplies the motion-planning details that a basic robot model does not contain. It must be used together with the URDF export.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when a robot assembly needs named arm or gripper groups, end-effectors, pose snapshots, or collision rules for a motion-planning system.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/w1ne/kernelcad-web/kernelcad-srdf
Install

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.

Any agent
npx skills add w1ne/kernelCAD-web --skill kernelcad-srdf
Clone the repo
git clone --depth 1 https://github.com/w1ne/kernelCAD-web

Made for: Claude Code, 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 kernelcad-srdf

README.md
[![agentmods](https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-srdf/github.svg)](https://agentmods.dev/skills/w1ne/kernelcad-web/kernelcad-srdf)
Your own site
<a href="https://agentmods.dev/skills/w1ne/kernelcad-web/kernelcad-srdf"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-srdf/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 kernelcad-srdf

Your own site · 80×15
<a href="https://agentmods.dev/skills/w1ne/kernelcad-web/kernelcad-srdf"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-srdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 744 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 $0.00050 $0.00744
Opus 5 $0.00025 $0.00372
Sonnet 5 $0.00010 $0.00149
Haiku 4.5 $0.00005 $0.00074

Measured 9d ago against content hash 8b33d6617083, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kernelcad-srdf 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.

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.

src/agent/skills/kernelcad-srdf/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kernelCAD — SRDF export

SRDF layers planning-group and motion-planner semantics on top of a URDF: which joints form an arm, which links form a gripper, which link pairs are safe to ignore for collision-checking, and named pose snapshots. kernelCAD's export({ target: 'model', format: 'srdf' }) writes the .srdf file; the allowed-collision matrix is auto-derived from the existing mate graph.

When to use

  • The assembly has at least one planning group declared via arm.planningGroup(...).
  • The downstream consumer needs motion-planner semantics (planning groups, end-effectors, named pose states, allowed-collision matrix).

Always pair with kernelcad-urdf: SRDF is a layer over URDF, not a standalone description.

Capture-time API

Five capture-time methods on the arm.* namespace. Each is declarative — the methods record intent; export materialises the SRDF later.

arm.planningGroup('main', { chain: { baseLink: 'base', tipLink: 'tool_tip' } });
arm.planningGroup('gripper', { joints: ['gripper-open'] });
arm.endEffector('tool', { parentLink: 'tool_tip', group: 'gripper', parentGroup: 'main' });
arm.virtualJoint('world_joint', { type: 'fixed', parentFrame: 'world', childLink: 'base' });
arm.groupState('home', 'main', { 'shoulder-pitch': 0, 'elbow-pitch': 0 });
arm.disableCollision('linkA', 'linkB', { reason: 'User' });

Allowed-collision matrix (ACM)

Auto-derived from the existing kernelCAD data. Four reasons:

  • Adjacent — link pair shares a joint or mate; never collides during motion.
  • Never — link pair never overlaps across pose-envelope samples (default 4 samples per limited mate; full sampling pass lands in a follow-up slice — today the deriver returns Adjacent + User only).
  • Default — link pair interferes at the default pose (broken model; disable to avoid spurious plan blocks).
  • User — explicit arm.disableCollision(linkA, linkB, { reason: 'User' }) override.

Sampling configuration:

// MCP: pass options on export.
export({ target: 'model', format: 'srdf', file: 'arm.kcad.ts', output_path: 'out/robot.srdf',
         options: { samplesPerMate: 4, combinatorial: true } });

Read the full file on GitHub · 55 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. 9d ago First seen · 55 lines · 50 tokens per session scan A 8b33d6617083

Subscribe to this mod's changes

kernelcad-srdf is a skill published in the GitHub repository w1ne/kernelCAD-web (19 stars, last pushed 11d ago), licensed MIT. It adds 50 tokens to every session and 744 once invoked, about $0.0003 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

cadquery-modeling

Generate CAD models with CadQuery using an adaptive CAD Compiler workflow: plan-mode skill constraint handoff, focused iteration scopes, fail-first challenge review, compact review packets, real-product reference fidelity, visual/functional audits, source-first repair, and STEP/STL export. Use for CadQuery, CQ, 建模…

armpro24-blip/cad-cae-copilot · 0 tokens

opengis-skills

Use when AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise for 73+ open-source projects. One-stop skill index with tag-based search and on-demand loading for GDAL, GeoServer, QGIS, PostGIS, JTS, CesiumJS, FreeCAD, OpenSCAD, OCCT, NPOI, SqlSugar, Furion, Dify, SuperSplat, Go and more.

znlgis/opengis-skills · 97 tokens

cad-skills

Use when doing parametric 3D modeling, 2D drafting, geometric kernel development, BIM/IFC processing, PCB design, or AutoCAD .NET development. Index of 20 skills: FreeCAD, OpenSCAD, OCCT, CadQuery, KiCad, SolveSpace, QCAD, xBIM, Clipper2, TongWen and more.

znlgis/opengis-skills · 81 tokens

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

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