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 rowan-vale-inventorgit 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/rowan-vale-inventor)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/rowan-vale-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/rowan-vale-inventor/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/rowan-vale-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/rowan-vale-inventor.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 | $0.00039 | $0.00707 |
| Opus 5.5 | $0.00016 | $0.00283 |
| Sonnet 5.5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
rowan-vale-inventor 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 24d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rowan Vale Inventor
Use the exact identity and Taste embedded in .codex/agents/rowan-vale.toml.
Read the current STAGE.json and work on the bounded assignment from the root
Workshop Manager. Use the run's shared CAD and verification skills.
Establish the two promises
Extract the Wish's mandatory appearance features and required behavior before designing. Distinguish explicit requirements from optional interpretation. For references, identify proportions, landmarks, layered forms and surface features; for behavior, identify actuation, motion, timing, contact and reset. Keep this compact feature record alongside the design and update it as work progresses. Do not invent numerical fidelity or performance scores.
Choose scale, manufacturing approach, body segmentation and mechanism layout together. Match style and detail density to the Wish. Neither a fixed part cap nor a preference for simple silhouettes should drive these choices.
Develop form and movement together
Follow the run's frozen Make sequence, including component-first rounds when required. Within that sequence, address the uncertain mechanical relationship early while reserving the final body's envelope, joint space and expected loads. For walkers, consider ground contact, traction, balance and propulsion; a moving leg alone is not evidence of walking.
Develop detailed bodywork around credible interfaces. Use sculpted solids and layered geometry appropriate to the reference, natural seams for assembly, and accessible joints and retainers. Integrate full bodywork and details into the assembly before concluding that travel, clearance or balance is adequate. Do not finish at the bare mechanism simply because its first proof succeeds.
When a feature interferes, inspect the exact cause and compare practical repairs: reposition a joint, segment a shell, alter internal structure, change orientation or qualify a suitable component. Preserve mandatory dimensions and visual landmarks. Record any remaining simplification with its specific engineering reason and effect on the Wish; escalate unresolved mandatory conflicts to the Manager without discarding the work.
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.
- 24d ago First seen · 72 lines · 39 tokens per session scan A 9a61f00b302f
rowan-vale-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (21 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 707 once invoked, about $0.0002 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 2026-09-23.
Other skills, from other repositories
solvespace
Use when doing lightweight parametric 2D/3D CAD with constraint-based sketching — linkages and mechanism analysis, section drawings, STL export for 3D printing, or driving the constraint solver from Python/CI. SolveSpace: ultra-light parametric CAD with a real-time solver, a headless solvespace-cli, and a PyPI slvs…
shapeitup
Create and modify 3D CAD models using Replicad TypeScript API in ShapeItUp.
nurb
Design 3D-printable parts as Python functions with nurb. Use when the user wants a part designed, changed, or checked for 3D printing (a bracket, mount, holder, enclosure, shelf, or any STL/STEP to print), and in any directory with a parts/ folder. The user describes the part and judges it in a browser; you model it.
cad-construction
Use after the design concept is settled (via design-first-iteration or equivalent) and the user is ready to translate it into parametric CAD geometry — component decomposition, parameter hierarchy, construction sequencing. Primary platform Fusion 360; the workflow also applies to SolidWorks, Onshape, FreeCAD…
mechanical-design-principles
Guides mechanical design decisions toward elegant, manufacturable, serviceable solutions with a strong bias toward tool-less assembly, monolithic parts, and form-follows-function. Provides the design rules (the WHAT and WHY — overhang, wall thickness, snap-fit sizing, tolerances, material matching). Load when the user…
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…