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 skills add autonomous-ai/autonomous-workshop --skill image-to-cadgit clone --depth 1 https://github.com/autonomous-ai/autonomous-workshopWrote 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/autonomous-ai/autonomous-workshop/image-to-cad)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/image-to-cad"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/image-to-cad/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.
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/image-to-cad"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/image-to-cad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.11872 |
| Opus 5.5 | $0.00050 | $0.04749 |
| Sonnet 5.5 | $0.00025 | $0.02374 |
| Haiku 4.5 | $0.00013 | $0.01187 |
Grade A, and why
image-to-cad 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 7d 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 — 922 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion verification is opt-in. Standalone make_round and verify_project
default to false; pass --check-motion true to enable it. Inside Workshop,
read the immutable run-root MAKE-OPTIONS.json: the tools inherit its
check_motion value and reject contradictory flags. A missing options file
in an older materialized run retains its mandatory motion policy. When false,
skip motion sweeps and required animation/reconstruction/review, even if a
manifest or assembly claims exist. Motion is unverified, never passed; do not
claim assemblability or working motion from skipped evidence. Build, fit,
print gates and still-image review remain required. These rules take
precedence over motion-specific requirements in references and templates.
image-to-cad — read a reference image into a buildable CAD spec
Purpose
Convert one or more reference images into a build spec precise enough that
cad writes <name>.step.py and its gen_step() from it with no second look
at the photo.
No image, only words: this skill does not apply. A prose request whose design
is open goes to $product-design, which writes the same spec from a product
survey and a concept selection instead of a photograph.
You produce a document, not geometry. No .py, no STEP, no STL. Fill
templates/build_spec.md — plus templates/build_spec_powered.md when a load
is functional or a part is driven — and hand off to cad.
Seven sections in this order, plus an eighth when the object has a functional electrical load or moves under power:
- Overall read — what it is, archetype, construction family.
- Top view (plan, down −Z).
- Front view (elevation, along +Y).
- Side view (elevation, along +X) — then 4b, every visible component in words, before any decision about parts.
- Size — mm, with the scale anchor that produced them.
- Decomposition and design selection — printed parts, feature trees, research logs, one evidence-backed selected design per active domain.
- Per-feature detail + build123d operation — geometry, numbers, API call, plane/selector, boolean order.
- Powered system / mechanism — power boundary and loads; when driven, also archetype, kinematic parameters, feasibility assertion, motion conditions.
What ships with it
16 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 269 B
- references/build123d-operations.md 4.3 KB
- references/decomposition.md 3.3 KB
- references/high-likeness-organic.md 3.2 KB
- references/likeness-gate.md 15 KB
- references/repeated-scene.md 1.7 KB
- references/scale-anchors.md 1.7 KB
- references/view-inference.md 5.4 KB
- requirements.txt 648 B
- scripts/check_likeness.py 58 KB runs code
- scripts/grid_overlay.py 3.0 KB runs code
- scripts/measure_image.py 62 KB runs code
- scripts/ref_silhouette.py 41 KB runs code
- scripts/render_views.py 93 KB runs code
- templates/build_spec_powered.md 12 KB
- templates/build_spec.md 21 KB
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.
- 7d ago Changed · +11 lines 5d11b9ceac53
- 1mo ago Changed · +9 lines f2a98a2304f3
- 1mo ago Changed · -5 lines c15de510b75f
- 1mo ago Changed · +12 lines a942bd834f2d
- 1mo ago Changed · +2 lines d312ad02b9f9
- 1mo ago Changed · -319 lines e921432e71d5
- 2mo ago Changed · +27 lines 59f505843165
- 2mo ago First seen · 1,185 lines · 125 tokens per session scan A 2a41088636ba
image-to-cad is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 125 tokens to every session and 11,872 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.
image-to-cad compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| image-to-cadautonomous-ai/autonomous-workshop | Skill | 24 | yesterday | Apache-2.0 | A | 125 | Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| analyze-marketlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 34 | Claude Code, Codex |
| haikuagno-agi/agno | Skill | 43k | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |