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 | $0.16182 |
| Opus 5 | $0.00063 | $0.08091 |
| Sonnet 5 | $0.00025 | $0.03236 |
| Haiku 4.5 | $0.00013 | $0.01618 |
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 5d 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 — 1,212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-to-cad — read a reference image into a buildable CAD spec
Purpose
A reference image is the densest brief a user can give and the easiest to
misread. This skill converts one (or several) images into a build spec: a
document precise enough that the cad skill can write <name>.step.py and
its gen_step() straight from it, with no second look at the photo.
You produce a document, not geometry. No .py, no STEP, no STL. The
deliverable is the spec in templates/build_spec.md, which hands off to
cad.
The spec has seven sections, in this order, and an eighth when the object has a functional electrical load or moves under power:
- Overall read — what the object is, its archetype, its construction family.
- Top view (plan, looking down −Z).
- Front view (elevation, looking along +Y).
- Side view (elevation, looking along +X) — then 4b, component descriptions: every visible component written out in words, before any decision about parts.
- Size — real-world dimensions in mm, with the scale anchor that produced them.
- Decomposition and design selection — printed parts, feature trees, research logs, then one evidence-backed selected design for every applicable exterior, mechanical, electrical, lighting and bought-device domain.
- Per-feature detail + build123d operation — one row per feature: geometry, numbers, the exact API call, the plane/selector it runs on, boolean order.
- Powered system / mechanism — the power boundary and electrical loads; when a part is driven, also the archetype, kinematic parameters, feasibility assertion and motion conditions.
The one rule that makes this skill work
A single photo shows you one viewpoint. The other two views are not in the image — you reconstruct them. Say so, every time, per fact:
| Tag | Meaning | Allowed to become a hard dimension? |
|---|---|---|
[observed] |
Directly visible and measurable in the image | Yes |
[inferred] |
Not visible, but forced by symmetry, function, or another observed fact — state the reasoning | Yes, with the reasoning shown |
[assumed] |
Neither visible nor forced; a default you chose | Yes, but flagged in the Assumptions list as user-correctable |
What ships with it
15 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 19 KB
- references/decomposition.md 8.7 KB
- references/high-likeness-organic.md 7.0 KB
- references/likeness-gate.md 15 KB
- references/repeated-scene.md 2.7 KB
- references/scale-anchors.md 7.0 KB
- references/view-inference.md 11 KB
- requirements.txt 648 B
- scripts/check_likeness.py 51 KB runs code
- scripts/grid_overlay.py 3.0 KB runs code
- scripts/measure_image.py 47 KB runs code
- scripts/ref_silhouette.py 11 KB runs code
- scripts/render_views.py 50 KB runs code
- templates/build_spec.md 32 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.
- 5d ago Changed · +27 lines 59f505843165
- 9d 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 (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 125 tokens to every session and 16,182 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
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…