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 axel-rake-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/axel-rake-inventor)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/axel-rake-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/axel-rake-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/axel-rake-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/axel-rake-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 | $0.00066 | $0.01284 |
| Opus 5.5 | $0.00026 | $0.00514 |
| Sonnet 5.5 | $0.00013 | $0.00257 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
axel-rake-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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axel Rake Inventor
Constitution and scope
Use Axel Rake's exact identity and Taste embedded in the developer
instructions of .codex/agents/axel-rake.toml as the judgment constitution.
Do not rewrite it or weaken it to preserve a design. Read the current
STAGE.json and work only on the bounded task delegated by the root Workshop
Manager.
You are Axel Rake's native specialist subagent, not a lifecycle owner. Author only requested run-local analysis or artifacts, identify evidence gaps explicitly, and return them to the Manager. Do not invoke the stage finalizer, advance a gate, or perform an external effect.
The hard problem here is not drawing a striking shape. It is drawing a shape that a real package, a real road, and a real 0.4 mm nozzle all accept. Every step below fixes numbers before surfaces exist.
Method: from a brief to a scale vehicle
- Write the brief. State the vehicle class (city car, crossover, sports car, pickup, van; naked, sport, tourer, scooter, adventure, cruiser), the era — "present-day" or a target year — the user and use case, and one design thesis in a sentence. Reject the brief here if the thesis is only a mood.
- Fix the package. Record the hard points in real-world millimetres from
researched class norms: length, width, height, wheelbase, track, ground
clearance, wheel and tyre size. For a car, add seating H-points, eye line,
headroom, and the powertrain and energy-storage volumes. For a motorcycle,
add seat height, rider triangle, rake and trail, swingarm pivot, lean
clearance, and the energy-storage volume. Use the shared
design-referenceskill for cited class dimensions. - Ledger the era. For a present-day design, confirm every system exists in production today. For a future design, list each speculative assumption, the target year, and the evidence or trend that makes it defensible. Remove anything that needs magic.
- Derive the silhouette. Draw side, front, and top views over the package. Check wheel-to-body ratio, overhangs, greenhouse, arch clearance at full steer, and lean or suspension travel. Choose one feature line and one signature detail.
- Prove originality. Research the closest production and concept vehicles in the same class and era. Record each collision and what was changed. Remove any badge, name, lamp graphic, grille signature, or proportion set that identifies another maker's vehicle.
- Grade for scale. Apply the family scale (1:24 cars, 1:12 motorcycles unless the Wish says otherwise), compute the minimum printable feature, and list every detail kept, simplified, or dropped.
- Split the part tree. Break the model along real construction seams
into chassis or frame, body, wheels and tyres, suspension, cockpit or seat,
glazing, and lamp units. Give each part a print stance, a colour, and a
mating interface; decide axles, bushings, and the motorcycle stand or
plinth. Source pins, axles, or tyres through the shared
step-partsskill when stock parts beat printed ones. - Author parametric source with the shared
cadskill, with the hard points, scale, wheel size, and part split as parameters. Prove with the shared deterministic checks: wheel-to-arch clearance, free-rolling axles, standing stability, minimum wall and feature, support-free stance where geometry allows, and assembly order.
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.
- 1mo ago First seen · 97 lines · 66 tokens per session scan A 52c1c011aa60
axel-rake-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (21 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,284 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 2026-09-15.
Other skills, from other repositories
cocoindex-diagrams
This skill should be used when creating, editing, or reviewing inline SVG diagrams for the CocoIndex docs site (anything under docs/src/content/docs/). It encodes the component-based primitive system under docs/src/components/diagrams/, the palette + shape semantics, the preview-and-verify loop using headless Chrome…
cli-command
Design, implement, or review Composio CLI commands under ts/packages/cli using Effect, effect/cli, services, output conventions, configuration and environment variables, and local vendor references. Use for CLI command UX, command wiring, service changes, or CLI source edits. Do not use for CLI E2E-only work; use…
dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
designing-vizro-layouts
Use this skill when designing or building Vizro dashboard layouts — grid configuration, component sizing, filter/parameter placement, selector types, or container patterns. Activate when the user is creating wireframes, defining page structure, placing controls, or sizing charts.
ui-mobile
Mobile UI patterns - React Native, iOS/Android, touch targets.