luma-vale-inventor

luma-vale-inventor is a skill for Claude Code, Codex from autonomous-ai/autonomous-workshop. It costs 61 tokens per session (747 once invoked), scanned A, original, Apache-2.0.

A specialist method for designing small optical objects that change what people see through moving openings, silhouettes, shadows, moiré patterns, or layers of light. It focuses on physical, hand-operated parts rather than electronics.

In plain words
What is it for?
Use it when designing support-free printed optical toys involving apertures, masks, rotors, shadows, moiré, or layered light.
Why use it?
It gives a structured way to turn a visual idea into a working object with defined layers, movement, clearances, and viewing states. The input does not describe general-purpose software or coding work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it when designing support-free printed optical toys involving apertures, masks, rotors, shadows, moiré, or layered light.

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

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

agentmods 80×15 button for luma-vale-inventor

Your own site · 80×15
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/luma-vale-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/luma-vale-inventor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 747 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 $0.00061 $0.00747
Opus 5 $0.00030 $0.00374
Sonnet 5 $0.00012 $0.00149
Haiku 4.5 $0.00006 $0.00075

Measured 10d ago against content hash ba6709703280, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

luma-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 10d 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/luma-vale/skills/luma-vale-inventor/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Luma Vale Inventor

Use the exact Inventor identity and Taste embedded in the developer instructions of .codex/agents/luma-vale.toml as the creative constitution. Do not rediscover or substitute identity from another file. Read the current STAGE.json, accept only a bounded task from the root Workshop Manager, and return precise evidence and artifacts.

Method

Design one physical optical transformation around a deliberate hand motion. State the light path or viewing path, layer order, moving interface, readable states, and the geometric reason the illusion changes. Make the inactive state beautiful enough to keep on a desk and the transformed state surprising enough to demonstrate twice.

Prefer two to four support-free parts: a stable frame, one or two masks or rotors, and an obvious retainer. For every interface, state the axis, range, clearance, stop, overlap, touch surface, assembly path, and print stance. Treat minimum web widths, aperture spacing, trapped shadows, layer separation, and ambient-light limits as product facts. Use exact monochrome geometry first; color may enrich but never rescue the effect.

Stage contributions

  • Invent: Explore at least three materially different optical mechanisms, such as rotating masks, sliding shutters, view-through alignments, moiré fields, or cast-shadow scenes. Research or deliberately choose the envelope, wall and web thicknesses, aperture sizes, viewing or projection distance, light assumptions, print stance, and failure risks. Seal each component's form, dimensions, placement, interfaces, layer order, and intended visual states precisely enough that Make does not have to invent the illusion.
  • Make: Use shared Workshop CAD skills to build the exact light and motion geometry. Inspect isolated layers and assembled states; prove clearances, stops, retention, minimum walls and webs, support-free orientation, and the claimed alignments from exact output. Generate product-derived renders for the inactive state, transformed state, exploded assembly, and one close optical view. If exact geometry proves the sealed concept cannot satisfy its own optical or mechanical requirements, preserve that evidence for the bounded Make-to-Invent route instead of silently changing the concept.
  • Playtest: Exercise the exact motion through every stop and evaluate each claimed visual state against explicit geometry or render evidence. Check discovery, reset, layer-order clarity, and legibility in monochrome. Distinguish deterministic optical/CAD evidence from physical light behavior or human delight that was not actually observed.
  • Release: Make the manual feel like a tiny observatory built around the exact toy. Lead with a dramatic product-derived hero, then teach assembly and the decisive motion with consistent views of the real geometry. Include inventory, layer order, setup, several light/viewing experiments, reset, care, and safety. Reject generic stars, decorative diagrams, or fabricated photos that cannot be traced to the sealed product.

Read the full file on GitHub · 62 lines

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. 10d ago First seen · 62 lines · 61 tokens per session scan A ba6709703280

Subscribe to this mod's changes

luma-vale-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (11 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 747 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

mem0-vercel-ai-sdk

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…

mem0ai/mem0 · 146 tokens

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

mine

Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.

MemPalace/mempalace · 21 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens