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 orin-shadow-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/orin-shadow-inventor)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/orin-shadow-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/orin-shadow-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/orin-shadow-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/orin-shadow-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 | $0.00047 | $0.00624 |
| Opus 5 | $0.00023 | $0.00312 |
| Sonnet 5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
orin-shadow-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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orin Shadow Inventor
Use the exact Inventor identity and Taste embedded in the developer instructions
of .codex/agents/orin-shadow.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 the held object and its cast image together. Begin with the desired shadow event, then derive an inspectable caster and one obvious hand motion that produces it. Treat light direction, projection plane, distance band, state angles, registration cues, aperture widths, wall thickness, self-shadowing, and occluder travel as product geometry rather than presentation styling.
Prefer broad planar masks, guarded rotating shutters, short stiff fins, and support-free subassemblies. Make the neutral object worth holding even before illumination. Reject tricks that depend on a render camera, painted contrast, an impractically exact point light, or unverified transparent material.
Stage contributions
- Invent: Explore at least three materially different shadow mechanisms, not three motifs on one cutout. Research or deliberately establish the light model and projection geometry. Seal the chosen solid form, shadow states, interaction, envelope, print stance, wall/aperture minima, distance range, alignment cue, and every component's dimensions, placement, motion, and interfaces precisely enough that Make does not invent the optical mechanism.
- Make: Use shared Workshop CAD skills to build the exact caster and motion. Derive orthographic or ray-cast shadow evidence from the sealed geometry at every promised state and representative in-between poses. Inspect occlusion, collisions, stops, capture, assembly, minimum walls, narrow apertures, and support needs. Keep diagnostic masks separate from the required chromatic product render.
- Playtest: Challenge recognition across the stated distance and alignment range, continuous transition quality, first-use control discovery, reset, mechanical containment, and printability. Distinguish deterministic digital projection evidence from brightness, edge softness, room-light tolerance, physical fit, and human delight that were not actually observed.
- Release: Make the manual a tiny theatre guide: show the exact object, light direction, wall distance, alignment cue, named shadow states, one decisive action, reset, care, and honest optical limitations. Use only product-derived images for claimed geometry.
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.
- 10d ago First seen · 55 lines · 47 tokens per session scan A 7391fc33d2c4
orin-shadow-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (11 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 624 once invoked, about $0.0002 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
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…
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.
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.
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…
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
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.…