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/open-software-network/os-clovy/os-designnpx skills add open-software-network/os-clovy --skill os-designgit clone --depth 1 https://github.com/open-software-network/os-clovyWrote 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/open-software-network/os-clovy/os-design)<a href="https://agentmods.dev/skills/open-software-network/os-clovy/os-design"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/os-design.svg" alt="Measured on agentmods" 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 | $0.00180 | $0.02117 |
| Opus 5 | $0.00090 | $0.01059 |
| Sonnet 5 | $0.00036 | $0.00423 |
| Haiku 4.5 | $0.00018 | $0.00212 |
Grade A, and why
os-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 6d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standing up design work at Open Software
This skill carries the house design sensibility so anyone on the team can stand up design-featuring work the way Andrew would, whether or not they have his reference tools (Mobbin) or his skill set installed. It makes two commitments that override any general design instinct or external skill advice:
- The system is the source of truth. Every OS repo with UI has design blocks already: tokens, primitives, patterns, documented rules. Compose from those blocks. Inventing a parallel treatment for something the system already answers is the primary failure mode this skill exists to prevent.
- Quiet is the default. The interface should read sharp, not loud. Structure comes from spacing and hierarchy, not decoration. A surface earns emphasis; it does not get it for free. When in doubt, choose the quieter option.
Before any pixels: ground in the system
Do this before writing or changing any UI code. Find and read the repo's design system:
| Repo | Where the system lives |
|---|---|
| os-clovy | docs/design/{foundations,components,conventions,taste}.md, enforceable rules in spec/ (read every spec in scope), tokens in src/styles/tokens.css, live gallery at styleguide.html (pnpm dev, then /styleguide.html?section=<id>) |
| os-scribe | src/styles/tokens.css |
| os-marketing-page | Tailwind theme + existing component families; per-repo judgment file if present |
| anything else | Look for docs/design/, DESIGN.md, a tokens.css / theme file, and a components or ui/ directory |
Then follow these rules without exception:
- Token before value. Reach for an existing token (spacing, radius, shadow, type size, duration, easing, color) before hand-coding a number. If a value genuinely needs to exist and no token covers it, extract a new token so the system gains a knob, rather than scattering literals.
- Primitive before bespoke. Check the repo's pattern-to-canonical map
(os-clovy:
docs/design/components.md) orui/directory before writing new markup for a button, input, toggle, select, tooltip, dialog, chip, empty state, spinner, or menu. If a canonical block exists, use it. - Grep before coining. In flat-CSS repos (os-clovy's
app.css), grep for a class name before creating it, and prefix by feature. - No system yet? Then the first deliverable of the work is the start of
one: mine the existing CSS for de facto tokens and write a short
foundations doc, rather than adding a third ad-hoc treatment. (If
impeccable is installed, its
document/extractcommands do this well.)
What ships with it
3 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.
- 6d ago First seen · 159 lines · 180 tokens per session scan A fa76250de94e
os-design is a skill published in the GitHub repository open-software-network/os-clovy (357 stars, last pushed 5d ago), licensed MIT. It adds 180 tokens to every session and 2,117 once invoked, about $0.0009 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
personal-commands
Edit hex.config.ts, not .hex-sdk. Config and installed dependencies execute with the user's normal permissions; use only trusted packages and avoid network, filesystem, environment, or subprocess access unless the requested command requires it. Run bun run check after editing.
hex-personal-commands
Configure HEX personal voice commands, voice-dictation control phrases, and deterministic transcript transformations. Use when the user wants to add or change commands or transformations for the HEX macOS voice app.
verify-dictation
The canonical "prove VZT Flow actually works" checklist — the human hotkey test plus its automated equivalents. Use before claiming a dictation-pipeline change works, before a release, or when the user runs /verify-dictation.
macparakeet-stt
Use when the user asks to transcribe audio or video, inspect or manage MacParakeet meeting recordings, search prior dictations/transcripts, or give an AI agent local speech-to-text tools on Apple Silicon.
release-murmur
Cut a signed, notarized macOS release of Murmur (Tauri 2 + Angular 22). The exact, proven step-by-step runbook — preflight gates → version bump (+ Cargo.lock sync) → JakubGawr commit → PR-merge to the murmur trunk (never direct-push) → rustup targets → stop dev → universal build → Developer-ID sign BY IDENTITY HASH…
ship-feature
Ship a Murmur feature through scope, isolated implementation, fresh adversarial and required security review, project gates, a JakubGawr commit, and a PR to murmur. Use the verifier-only Harness for risky, multi-step, or explicitly requested work; ordinary low-risk fixes keep the normal isolated-worktree route.