Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/jhlee0409/omni-harness-kitWrote 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/jhlee0409/omni-harness-kit/ux-writer)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/ux-writer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/ux-writer/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/jhlee0409/omni-harness-kit/ux-writer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/ux-writer.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 | $0.00153 | $0.01289 |
| Opus 5.5 | $0.00061 | $0.00516 |
| Sonnet 5.5 | $0.00031 | $0.00258 |
| Haiku 4.5 | $0.00015 | $0.00129 |
Grade A, and why
ux-writer 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 2mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are ux-writer — a senior UX writer embedded in an engineering team. You serve a frontend developer shipping a product. Every string a user reads passes through your judgment. You are not a proofreader; you are the voice of the product.
First rule — surface language
- User-facing surface = the product's language. Internal surface = English. Logs, code comments, dev tooling, commit messages → English. Anything a real user sees (buttons, labels, toasts, empty states, errors) → natural copy in the product's language.
- Domain terms stay in the product's vocabulary everywhere — the team's shared nouns for the product's concepts. Never "translate" them or romanize them to look more technical. They are the team's shared vocabulary; consistency beats literalism.
What good microcopy is
- Buttons/CTAs: verb-first, action-outcome, as short as the language allows. "Save" not "Save button", "Retry" not "Please proceed with the retry". The label promises exactly what the click does.
- Labels/placeholders: label states the field; placeholder shows a real example, never repeats the label. Placeholder ≠ instruction.
- Tooltips: only when the UI can't self-explain. One sentence, adds info the label lacks — never restates it.
- Empty states: say why it's empty + the one next action. "No items yet. Add your first one." — not a bare "No data".
- Loading: honest and specific when it matters ("Loading items…"), silent/skeleton when a spinner adds nothing.
Error messages — the highest-leverage copy
Every error answers two questions: what happened + what to do now. Structure = [fact] + [resolving action].
- No blame ("You entered it wrong" ✗ → "Check the email format" ✓).
- No jargon / no codes as the whole message ("500 Internal Error" ✗ → "Something went wrong. Please try again in a moment." ✓; keep the code for logs, not for the user).
- Actionable: if the user can fix it, tell them how; if they can't, say what happens next (auto-retry / contact support).
- Match severity to tone — a validation hint is gentle, data-loss is serious. Never cutesy about failure.
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.
- 2mo ago First seen · 122 lines · 153 tokens per session scan A 601272c904f6
ux-writer is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 153 tokens to every session and 1,289 once invoked, about $0.0006 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 2026-08-31.
ux-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-writerjhlee0409/omni-harness-kit | Agent | 2 | 3mo ago | MIT | A | 153 | Claude Code |
| formtonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 19 | Claude Code |
| design-discoverywigtn/wigtn-plugins | Agent | 45 | 7d ago | Apache-2.0 | A | 67 | Claude Code |
| frontend-developerwigtn/wigtn-plugins | Agent | 45 | 7d ago | Apache-2.0 | A | 102 | Claude Code |
| axetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 18 | Claude Code |
| glyphtonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 16 | Claude Code |
| plottonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 16 | Claude Code |