Borrowing it
Nothing to install: this file belongs to kwakseongjae/oh-my-design. 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/kwakseongjae/oh-my-design/main/.claude/skills/omd-autopilot/SKILL.mdgit clone --depth 1 https://github.com/kwakseongjae/oh-my-designWrote 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/kwakseongjae/oh-my-design/omd-autopilot)<a href="https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-autopilot"><img src="https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-autopilot/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/kwakseongjae/oh-my-design/omd-autopilot"><img src="https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-autopilot.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.08057 |
| Opus 5 | $0.00049 | $0.04029 |
| Sonnet 5 | $0.00020 | $0.01611 |
| Haiku 4.5 | $0.00010 | $0.00806 |
Grade A, and why
omd:autopilot 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 9d 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 — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
omd:autopilot
Use this skill for an ordinary natural-language request to create a new product surface without requiring the user to name a skill, choose a reference, or set up the guided harness.
This is a separate workflow from omd:harness. Never claim to have approved or
bypassed its mandatory checkpoints.
Ownership
The current main host agent is the only implementation owner. Specialists are
read-only advisers. They may write only inside the current run's advisory
folders and must never edit DESIGN.md or product files.
State machine
DETECT— inspect the repository, real consumer route, stack, existingDESIGN.md, preferences, components, states, assets and protected behavior. WhenOMD_AUTHORITY_CONTROLLER_RUN_DIRis present, use that exact relative path as the one run directory; do not derive or substitute a slug. Create the run-scopedtask.mdwhile retaining the exact user-prompt bytes verbatim (extra clearly labelled code observations may follow, but may never be presented as user authority), then runautopilot-mission.cjs <project-root> <run-dir> bootstrap. This freezes the initial product tree and mission budgets before any product write.AUTHORITY_GATE— runscripts/design-council-prime.cjsin the run scope. Freeze its decision ledger before any product write.BOUNDED_COUNCIL— dispatch no more than three evidence-required, read-only lanes. Do not dispatch a lane for a settled decision. A generic authorized greenfield mission uses only the design-system and interaction lanes; locale/copy or explicit external-evidence needs may add one relevant third lane. After the authority handoff reachesPROPOSE_PLAN, runautopilot-council-plan.cjs <project-root> <run-dir>, dispatch exactly the listed roles exactly once and in parallel (in bounded external-controller mode, execute those same lanes inline per the budget section instead of spawning advisers), then collect each result once and runautopilot-council-reconcile.cjs <project-root> <run-dir>. The reconciled receipt is mandatory and never grants product-write authority. Every lane must write the exact JSON shape declared inplan.json. Never send a follow-up, retry, or reformat request for a malformed/missing adviser result; fail the council honestly and preserve implementation time instead.CONSEQUENTIAL_INTERVIEW— ask zero or one batch. Ask only unresolved product-authority decisions that materially change acceptance or the design system. A sufficiently authorized prompt proceeds without a question. Never create, infer, or editcouncil-intake.answers.jsonon the user's behalf; that file may contain only an actual user response relayed verbatim after the controller has enteredCONSEQUENTIAL_INTERVIEW. Unattended mode (--unattendedin the prompt, or.omd/config.json"unattended": true): there is no user to answer, so each question takes its first (recommended) option and the choice is recorded inloop-trace.json→autoSelected[]as{question, chosen, alternatives}so the decision is auditable afterwards. Options that delete or overwrite files that existed before the mission are never auto-selected — the mission fails that requirement honestly instead.council-intake.answers.jsonis still never written: auto-selection is a trace entry, not a user answer.DESIGN_SYSTEM_DISPOSITION— resolve exactly one ofreuse,establish,refresh, orsurface-local-only. A missing exact brand source is blocked. After the council handoff reachesPROPOSE_PLAN, run the installeddesign-system-plan.cjs <project-root> <run-dir>helper. Itsdesign-system-decision.jsonreceipt is mandatory before any product write.SYSTEM_PROOF— forestablishorrefresh, use the contract inreferences/design-system-contract.md. The design-system architect may propose; the main agent writes only run-scoped graph/provenance/coverage drafts. New generation, synthesis, refresh, and refactor are single-write Core v2: never emit legacy frontmatter or 13/15/16-section layouts. After thedesign-system-decision.jsonreceipt grantsestablish/refreshauthority, inspect the environment before preparing a review. WhenOMD_AUTHORITY_CONTROLLER_RECEIPTis present, the main agent is explicitly not the project owner: it must not run either approval helper, pass a--reviewer, assert--authority-transition-approved, calculate a hash, or choose a second output name. Author the three drafts once, with every interactive component declaring all seven state-applicability entries and every non-interactive component declaring only a reason (non-interactive error/success display variants do not require a focus-visible state).
What ships with it
23 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.
- references/component-craft.md 4.6 KB
- references/derivation-chain.md 3.8 KB
- references/design-system-contract.md 11 KB
- references/presets/catalog.json 265 KB
- references/presets/commerce.md 2.9 KB
- references/presets/editorial.md 1.7 KB
- references/presets/flavors/kr.md 13 KB
- references/presets/fundamentals.md 11 KB
- references/presets/genres/auth.md 10 KB
- references/presets/genres/checkout.md 13 KB
- references/presets/genres/commerce.md 2.9 KB
- references/presets/genres/dashboard.md 17 KB
- references/presets/genres/editorial.md 1.7 KB
- references/presets/genres/marketplace.md 2.3 KB
- references/presets/genres/onboarding.md 11 KB
- references/presets/INDEX.md 4.6 KB
- references/presets/marketplace.md 2.3 KB
- references/presets/primitives/display.md 21 KB
- references/presets/primitives/form.md 18 KB
- references/presets/primitives/navigation.md 17 KB
- references/presets/primitives/overlay.md 20 KB
- references/slop-gates.md 5.6 KB
- references/visual-quality-contract.md 11 KB
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.
- 9d ago Changed · +42 lines 921bc25f894a
- 13d ago First seen · 545 lines · 99 tokens per session scan A 579547704b60
omd:autopilot is a skill published in the GitHub repository kwakseongjae/oh-my-design (500 stars, last pushed 5d ago), licensed MIT. It adds 99 tokens to every session and 8,057 once invoked, about $0.0005 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
dembrandt
A TypeScript command-line tool that renders a web page with Playwright and examines its actual styles. It turns colours, typography, spacing, borders, shadows, animation curves, components, and breakpoints into structured design tokens.
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
brandmd
Extract a website's design system into a DESIGN.md file. Use when starting a new frontend project, rebuilding a site, or when the user wants AI-generated UI to match an existing brand.
montology
A repo's vocabulary as a database, enforced against the code by a tree-sitter scan — in every language it declares (Python, TypeScript/JS, Go, Rust, Swift, Java, Ruby, Elixir, C/C++, and more). Use BEFORE naming anything in code — a class, struct, function, type, module, table, column, endpoint, event, env var, CLI…
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…