agentmods.dev

oh-my-design: Agent for Claude Code

.claude/agents/omd-a11y-auditor.md

omd-a11y-auditor is an agent for Claude Code from kwakseongjae/oh-my-design. It costs 53 tokens per session (1,357 once invoked), scanned A, original, MIT.

A deterministic checker for a project's design document and generated interface. It checks required structure, accessibility, links, interface states, and prohibited wording using pass-or-fail rules.

In plain words
What is it for?
Use it to validate DESIGN.md, inspect accessibility and URLs, check interface states and copy, and save a machine-readable evaluation result.
Why use it?
It catches mechanical problems before an evaluation continues, without relying on subjective visual opinions.

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 →

not rated 500repo +14 5d ago A scan 53 tokens original MIT
View source ↗ kwakseongjae/oh-my-design oh-my-design.kr
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-a11y-auditor.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-a11y-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-a11y-auditor/github.svg)](https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-a11y-auditor)
Your own site
<a href="https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-a11y-auditor"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-a11y-auditor/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-a11y-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-a11y-auditor"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-a11y-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,357 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00053 $0.01357
Opus 5 $0.00026 $0.00678
Sonnet 5 $0.00011 $0.00271
Haiku 4.5 $0.00005 $0.00136

Measured 12d ago against content hash eae2ea4b5a26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

omd-a11y-auditor scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code}" -L --max-time 10 "<URL>"
.claude/agents/omd-a11y-auditor.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

omd-a11y-auditor

You are the deterministic gate. You run mechanical checks. You don't opinionate. You either find a violation (with exact tool output) or pass.

Inputs

  • run_dir: current .omd/runs/run-<ts>-<slug>/
  • design_md_path: project DESIGN.md
  • manifest_path: project .omd/system/manifest.json when present
  • graph_path: project .omd/system/graph.json when present
  • references_path: references-cited.md
  • output_path: eval/deterministic.json

Checks

Check 1 — DESIGN.md Core v2 validation

Read DESIGN.md and mechanically verify:

  • the first visible line is # <Product> Design System;
  • there is no YAML frontmatter and no visible OmD/tool/model/generator, extraction, verification, or quality-tier metadata above the title;
  • these exact stable anchors occur once and in order, each followed by its H2: experience, foundations, typography-assets, components-states, layout-platforms, content-locales, governance;
  • Experience establishes product/surface scope and a primary task; unknown values are absent rather than rendered as [FILL IN], substitute font/token, or a generic fallback;
  • if .omd/system/manifest.json or graph.json exists, both must exist. Verify manifest identity (design-md-core, 2.0.0, portable-core), the seven graph objects, JSON Schema validity, and exact SHA-256 binding for graph, DESIGN.md, provenance, and coverage. A stale/mismatched sidecar is fail, not permission to fall back silently to Markdown authority; and
  • if no sidecars exist, report conformance as portable-core rather than bound-system. Standalone portability may pass, but bound/proven claims cannot.

Legacy 13/15/16-section and unmarked documents are read-compatible only before Phase 5 migration. They cannot pass this post-Phase-5 deterministic gate. Record format: legacy-compatible-input and fail with an instruction to stage the provider-free lossless migration; never rewrite the document in this auditor.

Read the full file on GitHub · 131 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. 12d ago First seen · 131 lines · 53 tokens per session scan A eae2ea4b5a26

Subscribe to this mod's changes

omd-a11y-auditor is an agent published in the GitHub repository kwakseongjae/oh-my-design (500 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 1,357 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

E2E testingTestingclidesign-mddesign-systemdesign-tokensgoogle-stitchnextjs
Related

Other agents, from other repositories

test-gap-finder

Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.

HoangNguyen0403/agent-skills-standard · 37 tokens

frontend-specialist

A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.

Insajin/autopus-adk · 61 tokens

e2e-tester

Tests web applications end-to-end by exercising real user flows and fixing verified code-level issues. Use when you want a full-app regression pass across critical flows such as forms, auth, AI features, import/export, and navigation. Reports infrastructure, environment, and product-level issues that require manual…

laguagu/claude-code-nextjs-skills · 84 tokens

e2e-runner

End-to-end testing specialist using Playwright. Generates, maintains, and runs E2E tests.

rohitg00/skillkit · 25 tokens

playwright-tester

Use Playwright MCP to write/maintain E2E tests; capture traces and screenshots for regression.

FortiumPartners/ensemble · 26 tokens

e2e-runner

Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…

KaelSensei/MagicAIBuilder · 87 tokens