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 ghbalf/freecad-ai --skill optimize-skillgit clone --depth 1 https://github.com/ghbalf/freecad-aiWrote 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/ghbalf/freecad-ai/optimize-skill)<a href="https://agentmods.dev/skills/ghbalf/freecad-ai/optimize-skill"><img src="https://agentmods.dev/badge/skills/ghbalf/freecad-ai/optimize-skill/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/ghbalf/freecad-ai/optimize-skill"><img src="https://agentmods.dev/badge/skills/ghbalf/freecad-ai/optimize-skill.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 | $0.00026 | $0.00197 |
| Opus 5 | $0.00013 | $0.00098 |
| Sonnet 5 | $0.00005 | $0.00039 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade A, and why
optimize-skill 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 9d 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.
The source is not reproduced here
Licensed LGPL-2.1
The repository is licensed LGPL-2.1, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
1 file 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.
- 9d ago First seen · 25 lines · 26 tokens per session scan A 071b2ae9c46d
optimize-skill is a skill published in the GitHub repository ghbalf/freecad-ai (476 stars, last pushed yesterday), licensed LGPL-2.1. It adds 26 tokens to every session and 197 once invoked, about $0.0001 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
freecad
Use when doing parametric 3D CAD modeling, BIM/architectural design, FEM simulation, CAM toolpath generation, or robot simulation with Python scripting. FreeCAD: the leading open-source parametric 3D CAD with Sketcher, Part, PartDesign, Arch, CAM, and FEM workbenches.
assembly
Build a multi-part assembly from component definitions, create instances, ground a reference frame, apply constraints incrementally, inspect degrees of freedom (DOF) after meaningful steps, detect over-constraint and interference, then export.
enclosure
Design a mechanically credible, FDM-friendly enclosure around measured component dimensions, with clearances, mounting features, connector openings, and verification before export.
fdm-dfm
Review an existing model for consumer FDM printability. Separate general geometric principles from printer/material/orientation-specific recommendations.
backend-diagnostics
Diagnose backend/FreeCAD worker failures using only public Battenmark status, capability, and structured-error surfaces. Never bypass the typed service layer.
basic-part
Create a simple, fully dimensioned solid part using parameters, common features, inspect, preview, and export an authoritative CAD artefact.