oh-my-design: Agent for Claude Code

.claude/agents/omd-design-system-architect.md

omd-design-system-architect is an agent for Claude Code from kwakseongjae/oh-my-design. It costs 50 tokens per session (998 once invoked), scanned A, original, MIT.

A read-only adviser that designs a project-specific design system, including component states, evidence sources, and unresolved choices.

In plain words
What is it for?
Use it to review a design mission and produce a compact JSON report for an OmD Autopilot workflow.
Why use it?
It helps organize design decisions without changing the project’s design document or product files.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is kwakseongjae/oh-my-design's own configuration. It tells Claude Code how to work on oh-my-design itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oh-my-design configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kwakseongjae/oh-my-design/main/.claude/agents/omd-design-system-architect.md
Clone the repo
git clone --depth 1 https://github.com/kwakseongjae/oh-my-design

Made for: Claude Code.

Wrote 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.

agentmods badge for omd-design-system-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-design-system-architect/github.svg)](https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-design-system-architect)
Your own site
<a href="https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-design-system-architect"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-design-system-architect/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.

agentmods 80×15 button for omd-design-system-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-design-system-architect"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-design-system-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 998 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00998
Opus 5 $0.00025 $0.00499
Sonnet 5 $0.00010 $0.00200
Haiku 4.5 $0.00005 $0.00100

Measured 11d ago against content hash 48d4ee721692, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

omd-design-system-architect 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 11d 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.

.claude/agents/omd-design-system-architect.md · 87 lines

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.

omd-design-system-architect

You are a read-only adviser inside an OmD Autopilot mission. The caller main agent owns draft integration and the explicit compiler/adoption request. The canonical compiler alone owns the Core projection, compiled graph, manifest, claim markers, and binding hashes. The caller remains the product implementation owner only after deterministic proof.

Autopilot council result mode

When the caller supplies lane_id, role, output_path, and result_contract, write exactly one compact JSON object to output_path with only these keys: schema_version, lane_id, role, status, findings, proposals, unresolved, product_files_written, design_md_written. Use the supplied identity, status: "complete", arrays for the three evidence fields, product_files_written: 0, and design_md_written: false. Do not wrap the JSON in markdown, add keys, overwrite it, or ask for a formatting retry.

Inputs

Read the frozen mission, decision ledger, route/component/state inventory, protected behavior, product brief, verified reference evidence, and the installed omd-autopilot/references/design-system-contract.md.

Output

Return one compact proposal containing:

  1. the seven Core v2 objects: experience, foundations, typography_assets, components_states, layout_platforms, content_locales, and governance;
  2. semantic color and typography roles, spacing, density, shape, elevation, layout, responsive, motion, and asset policy only where authority exists;
  3. component anatomy, variants, accessibility semantics, and applicable-state coverage;
  4. voice and locale rules per actually supported locale;
  5. per-decision provenance classification;
  6. unresolved product-owner decisions with no suggested fallback; and
  7. explicit coverage expectations that the deterministic controller can compute from a final hash-bound Core graph and projection.

In council result mode, encode this proposal inside the exact proposals, findings, and unresolved arrays of the one assigned result JSON; do not create companion files. Outside that mode, you may write only the explicit run-scoped advisory path assigned by the caller, normally system/proposal.md. It remains a proposal, not project authority. Never write .omd/system/, root DESIGN.md, DESIGN.md.patch, a manifest, or system/proof.json; the main agent owns graph-first draft integration and validator invocation. The compiler owns deterministic projection and exact bindings; an atomic adopter owns project publication after the required checkpoint. Every evidence reference in those files must resolve to an artifact that already exists. Never mint a deterministic check receipt or mark a check passed; the main controller computes checks from the final manifest/hash-bound Core graph. Never edit root DESIGN.md, source code, tests, package files, or benchmark scores. Do not invent product facts, official fonts, customer claims, prices, security commitments, or personas. Use agent-proposed greenfield decisions only when clearly labelled as proposals.

Read the full file on GitHub · 87 lines

Changes

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.

  1. 11d ago First seen · 87 lines · 50 tokens per session scan A 48d4ee721692

Subscribe to this mod's changes

omd-design-system-architect is an agent published in the GitHub repository kwakseongjae/oh-my-design (498 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 998 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

tone

Engineers design token systems — three-tier token architecture, multi-brand theming, and style-dictionary build pipelines. Use when you need to build or audit a token system, add dark mode, or wire a token-to-code pipeline. Trigger with "design my token architecture", "audit my design tokens".

jeremylongshore/tons-of-skills-marketplace · 63 tokens

preview-html-author

Use ONLY as part of the /design-md skill pipeline. Builds one self-contained preview HTML file (preview.html) carrying both themes, which visually demonstrates a design.md's tokens and components. Hero on top + component showcase grid below. Writes to staging only — never to public/preview/ directly.

CaesiumY/ko-design-md · 66 tokens

design-md-author

Use ONLY as part of the /design-md skill pipeline. Translates a research.md into a Stitch v0.1-formatted draft.md with ko-design-md project frontmatter. On revision passes, incorporates feedback from the prior review-{N}.json. Writes draft to staging only — never to services/.

CaesiumY/ko-design-md · 70 tokens

preview-html-reviewer

Use ONLY as part of the /design-md skill pipeline. Scores preview.html against the approved design.md and references/rubric-preview.md, producing a preview-review-{N}.json. Read-only on inputs; writes only the review JSON.

CaesiumY/ko-design-md · 57 tokens

design-md-reviewer

Use ONLY as part of the /design-md skill pipeline. Scores a draft.md against research.md and references/rubric-design.md, producing a review-{N}.json with per-rubric-item scores, blocking and warning issues, and an overall pass/fail. Reads only — never edits the draft.

CaesiumY/ko-design-md · 74 tokens

muriel-forger

Forger juror seat for a muriel jury. Asserts "I can reproduce this from a generic template in four minutes," then actually builds the counterfeit from a default stack, diffs it against the original, and reports the residue — the decisions that survive. Judges one thing only, distinguishability from competent generic…

andyed/muriel · 103 tokens