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/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/jmet04/ai-apprentice/aicad-model-3d"><img src="https://agentmods.dev/badge/skills/jmet04/ai-apprentice/aicad-model-3d.svg" alt="Reviewed on agentmods" width="80" 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 5.5 | $0.00030 | $0.00208 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 76 tokens to every session and 519 once invoked, about $0.0003 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 2026-08-31.
aicad-model-3d compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aicad-model-3dJMET04/ai-apprentice | Skill | 1 | 2mo ago | MIT | A | 76 | Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |