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 manual-designgit 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/manual-design)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/manual-design"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/manual-design.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01668 |
| Opus 5 | $0.00019 | $0.00834 |
| Sonnet 5 | $0.00008 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
manual-design 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 7d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual design
Create the customer artifact that makes the toy understandable and delightful
at unboxing. The finished MANUAL.pdf must teach the complete supported use or
play experience without a website, phone, QR code, or prior explanation.
Design from the exact product
- Inspect the Wish, selected Taste, sealed product facts, exact geometry, component inventory, and passing Playtest findings before designing.
- Before laying out pages, commit to a short creative brief: the emotional promise, physical format and rationale, product-specific visual motif, palette, typography, and teaching arc. Use it to make the manual feel like part of this toy rather than documentation wrapped around it.
- Read references/product-manual-visual-system.md before layout. It captures the reusable visual grammar observed in the Workshop's strongest manuals and the report-like failure modes to reject.
- Depict only included parts and supported interactions. Prefer renders, silhouettes, exploded views, and diagrams derived from the exact product artifacts; do not invent geometry or imply unverified physical performance.
- Put an exact product-derived visual on the cover. A title over empty space, ASCII art, or an unstyled technical-report/manpage fallback is not an acceptable substitute for art direction.
- Choose the physical format to suit the toy and box: a card, foldout, leaflet, or booklet may each be right. Decide page size, orientation, page count, binding, margins, and bleed deliberately instead of defaulting every toy to one template.
- Use the smallest complete physical format and never add pages merely to make the guide feel substantial. Default a simple one-piece Spark toy with no assembly or rule system to one double-sided owner card. Add a page only when one specific setup, safety, reset, or interaction need cannot remain clear on that card. Games, assemblies, or products with real rule complexity may earn a longer booklet. These are design heuristics, not fixed page-count gates.
- Choose an authoring method that gives the concept the strongest print result. HTML/CSS-to-PDF, vector-native layout, and programmatic drawing are all valid. Do not force a generic visual template across products.
What ships with it
2 files 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.
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.
- 7d ago First seen · 142 lines · 39 tokens per session scan A a97b0aec3826
manual-design is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (11 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 1,668 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-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
gpu-document-processing
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document analysis.
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
cli-release
Release and recover first-party Composio CLI binaries through Build CLI Binaries, including automatic beta builds, promote-stable dispatches, beta-tag selection, asset and installation verification, and failed release recovery. Use when a contributor asks to build a CLI beta, publish or promote a stable CLI version…
extracting-keywords
Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), --detect-language, and the standalone embed command with real flags.