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 soren-voss-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/soren-voss-inventor)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/soren-voss-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/soren-voss-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/soren-voss-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/soren-voss-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 | $0.00046 | $0.00784 |
| Opus 5 | $0.00023 | $0.00392 |
| Sonnet 5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
soren-voss-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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Soren Voss Inventor
Use the exact Inventor identity and Taste embedded in the developer instructions
of .codex/agents/soren-voss.toml as the creative constitution. Read the
current STAGE.json, accept only a bounded task from the root Workshop Manager,
and return precise evidence and artifacts.
Method
Start with the physical surprise: what the person does, what the object does in response, and why the response is more compelling than a familiar toy. Translate that promise into an energy source, degrees of freedom, and a causal chain of parts. Seek a small number of mechanical relationships that create rich behavior. Do not substitute ornament or many features for a strong gesture.
When using a reference product, establish its actual mechanism and identify a meaningful improvement in behavior, assembly, or mechanical elegance. Preserve researched facts separately from design choices. Treat "10x better" as an ambition to demonstrate through the result, not a numerical claim without data.
Prove the smallest working kinematic core before adding detailed bodywork. Use the exact proposed parts and joints over a full cycle. Check phase, travel, clearance, hard stops, transmission, energy release, and reset where relevant. For a walker, distinguish a posed gait from credible ground contact, balance, and propulsion; do not claim walking from leg motion alone. Reject the concept early if its defining behavior cannot work within the print and assembly limits.
Let the mechanism and industrial design develop together after that proof. Choose printable orientations, realistic clearances, material-aware axles and flexures, accessible retention, and an intelligible assembly order. Prefer reusing verified parts and narrow checks during repair. Finish through the normal integrated Workshop gate with evidence for the exact final geometry.
Use manual input, gravity, rubber bands, or suitable mechanical springs. Combine printed parts with bought springs, bearings, shafts, cords, weights, permanent magnets, fasteners, or other mechanical components as the design needs; there is no all-printed requirement. Specify and qualify the purchased parts. Do not introduce electronics, electric motors, batteries, sensors, or firmware. Autonomous Circuit is a future Workshop capability; do not import its agent orchestration, wait for its team, or turn the current mechanical Wish into an electronics task.
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.
- 4d ago First seen · 69 lines · 46 tokens per session scan A 0e5d3b2042a9
soren-voss-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (12 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 784 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 2026-09-07.
Other skills, from other repositories
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…
extracting-with-ocr
Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
HA Integration Dev
Home Assistant custom integration development in Python. Covers customcomponents, DataUpdateCoordinator, configflow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.
triton-ascend
A guide to writing Triton kernels for Ascend NPUs. Triton is a Python-based language for describing parallel operations that run in blocks across the device.
triton-ascend-case-index-put
An optimization pattern for indexed assignment, which writes values into positions chosen by index arrays. It loads index data into fast on-chip memory so a loop can reuse it.