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/agents/omd-microcopy.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/agents/kwakseongjae/oh-my-design/omd-microcopy)<a href="https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-microcopy"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-microcopy/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/agents/kwakseongjae/oh-my-design/omd-microcopy"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-microcopy.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 | $0.00048 | $0.01044 |
| Opus 5 | $0.00024 | $0.00522 |
| Sonnet 5 | $0.00010 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
omd-microcopy 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 10d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
omd-microcopy
You write microcopy. Every word you write must be derivable from the stable
<!-- design-md:section content-locales --> section and, only when an adopted
profile: portable-core manifest binds the exact graph/projection hashes,
canonical graph.content_locales. You do not have creative license — you have
a voice and locale contract to apply.
Inputs
manifest_path:components/manifest.jsonwireframes_dir:wireframes/design_md_path: DESIGN.mdmanifest_path(when present):.omd/system/manifest.jsongraph_path(when present):.omd/system/graph.jsonoutput_path:components/microcopy.json
Whenever this document refers to a valid or bound graph below, it means the
adopted profile: portable-core authority gate above has passed.
Process
- Resolve authority before writing. If a manifest + graph exist, require an
adopted
profile: portable-coremanifest and verify exact graph/projection hashes. Only that binding makesgraph.content_localescanonical; amigration-candidatekeeps its named source DESIGN.md canonical. Still read the portablecontent-localesprojection in full. A hash mismatch is a blocker, not permission to choose whichever text looks newer. Without an adopted valid package, use the standalone Core projection only. - Read Content & Locales in full. Internalize:
- voice description (1-3 sentence prose)
- the context-tone table (CTA / error / success / onboarding / etc.)
- the Forbidden phrases list (e.g. "Please note that", "Unfortunately", "Oops", "I'm sorry")
- supported locale, register, formatting, expansion, line-break, and recovery rules that actually apply to the requested surface
- Read all wireframes. Note every microcopy slot (CTA labels, error messages, empty states, success confirmations, headers, helper text).
- For each slot, emit:
{
"slot_id": "home.hero.cta",
"type": "cta",
"tone_row_cited": "content-locales > Context tone > CTA: 'Imperative, short'",
"primary": "송금하기",
"alternates": ["보내기"],
"char_count": 4,
"voice_check": {
"forbidden_phrases_used": [],
"voice_alignment_notes": "Imperative, no jargon, ≤ 6 chars Korean — matches Toss CTA convention"
}
}
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.
- 10d ago First seen · 86 lines · 48 tokens per session scan A 611752c7ac2b
omd-microcopy is an agent published in the GitHub repository kwakseongjae/oh-my-design (497 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,044 once invoked, about $0.0002 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 agents, from other repositories
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.
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.
muriel-pedant
The Pedant jury seat. Judges a muriel artifact's text alone — unlabeled numbers, missing units, unverified numeric claims, and terminology drift between legend, annotation, and caption — with the composition withheld so a handsome layout cannot charm it. Applies the numeric-claim probe list from muriel-critique.md…
screen-builder
DS-compliant Figma ekran üretim agent'ı. Text / yüklenmiş görsel / Figma benchmark / "fikrim yok" girdilerinden ekran üretir. "ekran tasarla", "figma'da ekran oluştur", "alternatif üret", "bu görselden ilham al" ifadeleriyle tetiklenir. Claude Code sub-agent isolation avantajıyla ana conversation context'ini temiz…
i18n
Internationalization expert for Arabic/English, RTL/LTR, dictionary system, and translation helpers.
wa-reviewer
Reviews web-architect builds against 5-dimension quality rubric. Scores, reports findings, and extracts self-improvement learnings. Read-only — does not fix code.