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 agentmods add skills/lglucas/ai-dev-operating-system/prototype-labnpx skills add lglucas/ai-dev-operating-system --skill prototype-labgit clone --depth 1 https://github.com/lglucas/ai-dev-operating-systemWhat 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 | $0.00114 | $0.00432 |
| Opus 5 | $0.00057 | $0.00216 |
| Sonnet 5 | $0.00023 | $0.00086 |
| Haiku 4.5 | $0.00011 | $0.00043 |
Grade A, and why
prototype-lab 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 3d 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.
What it actually says
Prototype Lab Skill
Create three distinct HTML/CSS/JS prototype directions using the same mock data.
Runs at Phase 3 of WIZARD.md — before the Product Brief and the Technical Plan, not after.
Inputs
All prototypes must reflect BP v0.0.2 (personas, positioning, MVP scope, primary flow) and the research in knowledge-base/.
The Product Brief is NOT an input. It does not exist yet — Phase 4 derives it from the direction approved here. If you find yourself needing the Product Brief, the thing you actually need is missing from BP v0.0.2; go add it there.
Rules
- Three directions, genuinely distinct — not three shades of one idea.
- All three read the same file:
prototype-lab/shared/mock-data.js. Not "equivalent data" — the same file. Phase 4.2 derives the Technical Plan's entities from it, so it needs one guaranteed shared source. - Same core flows across all three, so the comparison is about design and not content.
- Each direction carries an explicit brand hypothesis: palette, typography, density, tone.
- Do not contaminate the production app with prototype code.
Output
After the user picks a direction, write docs/product/DESIGN-DIRECTION.md — tokens, typography scale, spacing, component inventory, screens, the flow as actually clicked, and what was rejected. That file is what Phase 4 reads.
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.
- 3d ago First seen · 29 lines · 114 tokens per session scan A 989ce6089df0
prototype-lab is a skill published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 24d ago), licensed MIT. It adds 114 tokens to every session and 432 once invoked, about $0.0006 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
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
industrial-brutalist-ui
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.