Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JMET04/ai-apprenticenpx agentmods add skills/jmet04/ai-apprentice/aicad-drawWrote 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-draw)<a href="https://agentmods.dev/skills/jmet04/ai-apprentice/aicad-draw"><img src="https://agentmods.dev/badge/skills/jmet04/ai-apprentice/aicad-draw/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-draw"><img src="https://agentmods.dev/badge/skills/jmet04/ai-apprentice/aicad-draw.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 | $0.00082 | $0.00748 |
| Opus 5 | $0.00041 | $0.00374 |
| Sonnet 5 | $0.00016 | $0.00150 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
aicad-draw 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI CAD Constraint Drawing
Use the bundled tools as the execution boundary. Do not emit raw AutoCAD commands from model text and do not hand-edit .aicad files.
Core workflow
- Call
aicad_capabilitiesonce when entity, constraint, or output support is uncertain. - Determine whether dimensions uniquely define the drawing. Ask one focused question when a fit-critical dimension is missing; otherwise state harmless assumptions.
- For a rectangle, circle, arc, or rectangular plate with one centered hole, call
aicad_generate. Keep its defaultprovider: offlineunless the user explicitly chose a configured provider. - For other supported 2D geometry, call
aicad_get_plan_schema, author a schema 2.0 plan, then callaicad_compile_plan. - Read the returned manifest and audit paths. Treat
ok: trueplus the generated manifest as the completion gate. - When visual review matters and a CAD renderer is available, hand the returned DXF path to it. Keep AutoCAD execution as a separate explicit step.
Plan every entity mathematically
For each entity, determine before submitting the plan:
- its functional purpose;
- the earlier point or entity it depends on;
- the minimum constraints that uniquely determine it;
- whether it closes, continues, parallels, or is perpendicular to earlier geometry;
- whether it duplicates geometry, has zero size, or creates an unintended gap.
Anchor the first line start or first radial center at origin. Prefer references to earlier endpoints, midpoints, and centers. Use an explicit origin-relative offset only when no earlier geometric point is appropriate.
Read plan-schema.md before authoring a non-template plan. Read examples.md for tool-call patterns. Read failure-recovery.md only after a tool rejects a request or plan.
Result handling
Return the most useful artifacts to the user:
.dxffor portable geometric review;.aicadfor the validated AutoCAD plugin executor;.scronly as an explicit AutoCAD script fallback;.audit.mdfor entity purpose, relations, and reasoning;.manifest.jsonfor hashes, counts, and artifact inventory;.plan.jsonas the editable source of truth.
What ships with it
4 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 · 59 lines · 82 tokens per session scan A b7b9d6ba0736
aicad-draw is a skill published in the GitHub repository JMET04/ai-apprentice (1 stars, last pushed 18d ago), licensed MIT. It adds 82 tokens to every session and 748 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.