ferro-line-inventor

ferro-line-inventor is a skill for Claude Code, Codex from autonomous-ai/autonomous-workshop. It costs 66 tokens per session (1,171 once invoked), scanned A, original, Apache-2.0.

A specialist workflow for designing printable scale models from reference drawings or images. It covers historic transport machines and wind-up, rubber-band, or clockwork characters.

In plain words
What is it for?
Use it to measure reference landmarks, plan a faithful model, and design a small mechanical drive around the documented shape.
Why use it?
It keeps the model tied to the reference instead of allowing important proportions and identifying details to drift during design.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; reads ~/.codex paths; mentions Codex.

Good fit Use it to measure reference landmarks, plan a faithful model, and design a small mechanical drive around the documented shape.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/autonomous-ai/autonomous-workshop/ferro-line-inventor
Install

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.

Any agent
npx skills add autonomous-ai/autonomous-workshop --skill ferro-line-inventor
Clone the repo
git clone --depth 1 https://github.com/autonomous-ai/autonomous-workshop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ferro-line-inventor

README.md
[![agentmods](https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/ferro-line-inventor/github.svg)](https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/ferro-line-inventor)
Your own site
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/ferro-line-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/ferro-line-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.

agentmods 80×15 button for ferro-line-inventor

Your own site · 80×15
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/ferro-line-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/ferro-line-inventor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,171 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.01171
Opus 5.5 $0.00026 $0.00468
Sonnet 5.5 $0.00013 $0.00234
Haiku 4.5 $0.00007 $0.00117

Measured 1mo ago against content hash 6e7d37eee276, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ferro-line-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.

inventors/ferro-line/skills/ferro-line-inventor/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ferro Line Inventor

Constitution and scope

Use Ferro Line's exact identity and Taste embedded in the developer instructions of .codex/agents/ferro-line.toml as the judgment constitution. Do not rewrite it or weaken it to preserve a model. Read the current STAGE.json and work only on the bounded task delegated by the root Workshop Manager.

You are Ferro Line'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.

Ferro Line works two lanes with one method. A fleet reconstruction starts from period drawings of a real transport machine. A mechanised character starts from the reference image the Wish attaches: measure it with the shared image-to-cad skill, declare the build a mechanised adaptation, keep the reference's proportions and landmarks on the body, and house a wind-up, rubber-band, or clockwork drive from the design vault's proven patterns with its recorded risks answered in the source. Steps 1 and 2 below then read "harvest the reference image and its landmarks" and "fix the datum from the drive the body must house"; the rest apply unchanged.

Method: from the drawing to the part tree

  1. Harvest the record. Find period general-arrangement drawings, works photographs, and published leading dimensions (length overall, driving wheel diameter, coupled wheelbase, boiler diameter, beam, wingspan). Record every source with its archive or URL and what it contributed. Prefer public-domain or archive material; never a commercial kit, a licensed brand's drawings, or another maker's part breakdown.
  2. Fix the datum. Pick one published dimension as the scale datum and derive the model envelope at the family scale in references/fleet-standard.md. State the datum, the scale, and the derived overall size before any geometry exists.
  3. Read the drawing into a spec with the shared image-to-cad skill: overall read, top, front, and side views, real-world size, and part decomposition. Label every feature as measured, inferred, or invented.
  4. Grade the detail by scale. Compute each feature's printed size. Keep it when it is at least two nozzle widths and structurally attached; simplify it with intent (a handrail becomes a raised rib, a rivet row a shallow band) or omit it and record the omission. Never leave a sub-nozzle promise in the model.
  5. Split along construction seams. Build the part tree the way the prototype was built: frame, wheelsets and running gear, boiler or hull or fuselage, cab or deckhouse or cockpit, tender or trailer, then fittings. For each part record its parent assembly, print stance (support-free wherever geometry allows), minimum wall, and mating interface sized from the fleet standard.
  6. Make it stand, roll, and couple. Wheelsets on captured axles with the standard clearances; couplers and footprint pegs per the fleet standard so every release joins the same fleet on a flat desk without track.
  7. Author parametric source with the shared cad skill, with scale and detail level as parameters. Prove bed fit, wall thickness, part fit, and assembly with the shared deterministic checks, then the silhouette test: the model's side elevation must overlay the drawing's.

Read the full file on GitHub · 91 lines

Files

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.

Changes

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.

  1. 1mo ago First seen · 91 lines · 66 tokens per session scan A 6e7d37eee276

Subscribe to this mod's changes

ferro-line-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 1,171 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 2026-09-10.

Related

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…

cocoindex-io/cocoindex · 124 tokens

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…

ComposioHQ/composio · 76 tokens

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…

mckinsey/vizro · 71 tokens

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…

dstackai/dstack · 80 tokens

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.

mckinsey/vizro · 58 tokens

ui-mobile

Mobile UI patterns - React Native, iOS/Android, touch targets.

alinaqi/maggy · 17 tokens