Borrowing it
Nothing to install: this file belongs to saschb2b/okf-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saschb2b/okf-studio/main/.agents/skills/odsf/SKILL.mdgit clone --depth 1 https://github.com/saschb2b/okf-studioWrote 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/saschb2b/okf-studio/odsf)<a href="https://agentmods.dev/skills/saschb2b/okf-studio/odsf"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/odsf/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/saschb2b/okf-studio/odsf"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/odsf.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 | $0.00231 | $0.03273 |
| Opus 5.5 | $0.00092 | $0.01309 |
| Sonnet 5.5 | $0.00046 | $0.00655 |
| Haiku 4.5 | $0.00023 | $0.00327 |
Grade A, and why
odsf 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Design System Format (ODSF)
ODSF packages a design system as a self-contained bundle an AI agent can read, navigate, and apply to a task, with no SDK, no platform, and no lock-in. It is a strict profile of Open Knowledge Format v0.2: everything OKF says about bundles, concepts, frontmatter, links, index.md, log.md, and versioning holds unchanged, including the v0.2 provenance and trust layer (sources, generated, verified, status, stale_after, and the actor convention). A design system is exactly the kind of knowledge that layer was added for, since "is this token still the brand's" and "has a human signed off on this component spec" are the questions an agent building UI from a bundle most needs answered. On top of that container ODSF adds three things: a token model (machine-readable design tokens, design.md's seed), companion HTML/CSS assets so a concept ships a concrete self-rendering example, and a design type vocabulary so foundations, components, patterns, behaviors, and guidelines are first-class. The goal is a bundle you hand to an agent ("build this screen, adhere to this design system") that produces work that looks and behaves the way the system intends.
Use this skill two ways. Run a command on demand, or apply it implicitly whenever you shape design knowledge an agent will build from. The normative spec lives in spec.md; per-command steps in commands.md; copy-paste starting points in templates.md.
The two rules
A bundle is a conformant ODSF bundle when both hold: it is a conformant OKF bundle (every non-reserved .md concept opens with YAML frontmatter carrying a non-empty type), and the bundle-root index.md declares odsf_version in its frontmatter. That is the whole hard requirement: be a valid OKF bundle, and say you are an ODSF one. Everything else (the token model, the asset conventions, the type vocabulary, the body sections) is recommended structure a producer SHOULD follow and a consumer MUST tolerate the absence of. An OKF-only consumer reads an ODSF bundle and loses only the design niceties. Full conformance and the consumer contract are in spec.md.
What ships with it
9 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.
- 3d ago First seen · 87 lines · 231 tokens per session scan A 9ae83e86eee5
odsf is a skill published in the GitHub repository saschb2b/okf-studio (47 stars, last pushed yesterday), licensed MIT. It adds 231 tokens to every session and 3,273 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-23.
Other skills, from other repositories
better-design
Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…
token-audit
Audit how design tokens are defined: tiers, naming, alias chains, raw values, orphans, DTCG readiness. Triggers: audit my tokens, token architecture review, token health check. Not for code consuming tokens (token-compliance), theme parity (theme-audit) or Figma variables (figma-variable-audit).
accessibility-per-component
Audit one design system component's accessibility against WCAG 2.2 AA: keyboard, screen reader, contrast, focus, ARIA, target size. Trigger: a11y audit, is this accessible, WCAG check, screen reader support, keyboard navigation check. Not for page- or product-wide audits.
component-decision-tree
Write "choosing between" pages (docs/choosing/) that route an intent to the right component via narrowing questions; YAML trees on request. Triggers: which component should I use, choose between X and Y, dialog vs drawer, selection guide. One chosen component: usage-guidelines.
figma-variable-audit
Audit Figma variable collections: tier mapping, naming, alias chains, modes, orphans; can fix in place with Figma Console MCP. Triggers: audit my Figma variables, review variable collections, Figma variable health. For token files in code use token-audit.
metadata-schema-generator
Generate per-component JSON metadata files (.ai/metadata/) from source: props, behaviour, composition, a11y contract, prohibited prop combinations. Triggers: component metadata schema, machine-readable component JSON, manifest for MCP/codegen. Prose for Figma: use ai-component-description.