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 JMET04/ai-apprentice --skill aicad-model-3dgit clone --depth 1 https://github.com/JMET04/ai-apprenticeWrote 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/jmet04/ai-apprentice/aicad-model-3d)<a href="https://agentmods.dev/skills/jmet04/ai-apprentice/aicad-model-3d"><img src="https://agentmods.dev/badge/skills/jmet04/ai-apprentice/aicad-model-3d.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 | $0.00076 | $0.00519 |
| Opus 5 | $0.00038 | $0.00260 |
| Sonnet 5 | $0.00015 | $0.00104 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
aicad-model-3d 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 8d 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.
What it actually says
AICAD Model 3D
Model slowly and transactionally: reason about one feature, validate it, execute it, read it back, then continue.
Workflow
- Call
aicad_capabilitiesandaicad_solidworks_doctor. - Decompose the part into an ordered feature graph. Start the base sketch at
[0,0,0]. - For every feature, state:
- purpose;
- relation to earlier features;
- dependency and support feature;
- profile dimensions and location;
- operation depth/end condition;
- expected volume delta and resulting bounds.
- Call
aicad_get_3d_plan_schema, then author a schema1.0plan. Read plan-schema.md when creating or editing the plan. - Call
aicad_validate_3d_plan. Correct the first reported invariant violation before execution. - Call
aicad_build_solidworks_partwithexecute=true. - Accept a feature only when its report passes all gates: fully constrained sketch, feature error code zero, fault-free single body, expected volume/delta/bounds, and persistent support reference resolution.
- Deliver the SLDPRT, STEP, audit, manifest, and SolidWorks report together. Summarize the feature-to-feature reasoning.
Hard rules
- Never issue raw mouse/keyboard CAD drawing as the primary modeling path.
- Never create all features first and inspect only the final shape.
- Never continue after a failed feature transaction.
- Never reference volatile names such as
Face1orEdge3in a plan. - Prefer principal planes and semantic support geometry. Require persistent-reference re-resolution after rebuild when topology is used.
- Treat a non-null feature object as insufficient evidence of success.
- Keep identifiers and the SolidWorks execution channel ASCII-safe; keep human explanations in UTF-8 plan/audit fields.
- Do not save a partial SLDPRT when any gate fails.
Read failure-recovery.md when execution fails.
What ships with it
3 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.
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.
- 8d ago First seen · 40 lines · 76 tokens per session scan A 48c0fb92aca4
aicad-model-3d is a skill published in the GitHub repository JMET04/ai-apprentice (1 stars, last pushed 18d ago), licensed MIT. It adds 76 tokens to every session and 519 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.