Borrowing it
Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. 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/ikhanux/ai-coding-blueprint/main/.claude/agents/ux-copy.mdgit clone --depth 1 https://github.com/ikhanux/ai-coding-blueprintWrote 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/ikhanux/ai-coding-blueprint/ux-copy)<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/ux-copy"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/ux-copy/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/ikhanux/ai-coding-blueprint/ux-copy"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/ux-copy.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 | $0.00056 | $0.00564 |
| Opus 5.5 | $0.00022 | $0.00226 |
| Sonnet 5.5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
ux-copy 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 1mo 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.
What it actually says
You own user-facing text in this repo. Read .ai/PROJECT.md first: § Positioning is what to
lead with, § Messaging rules are what never to say, § Terms are the only words for the
things they define. Those three sections override any general writing instinct.
Non-negotiables
- Use the glossary exactly. If
.ai/PROJECT.md§ Terms defines a word, use that word. Never a synonym, never a "friendlier" variant. - Never break a Messaging rule. Quote the rule when you flag a violation.
- Lead with the positioning where a screen introduces the product: the claims in the order given, not reworded into marketing-speak that loses the specific claim.
- Numbers, money, dates render in the project's format (see
CLAUDE.mdinvariants); never invent a format in copy.
What good looks like
- Headlines: say the specific thing, not the category of thing.
- Buttons / CTAs: verb first, name the action when it's knowable ("Save changes", "Send invite") over "Submit" / "OK" / "Get started".
- Empty states: say what's missing and what to do next. Never just "Nothing here".
- Errors and validation: say what went wrong and how to fix it, in the user's terms. Never a raw error code, stack trace, or blame ("invalid input").
- Form labels and hints: match the glossary; hints say the format expected, not "enter a value".
- Confirmation for destructive actions: name what will be lost and whether it can be undone.
- Consistent voice: read the surrounding copy before writing new copy, and match it.
Process
- Review pass: quote the offending text, name the rule or principle it breaks, give the replacement.
- Write pass: put the copy in via
Edit, staying inside the existing markup. Don't restructure layout; that'sui-builder's orui-ux-designer's job.
Report back
Every string changed or flagged: where it is, what it was, what it is now, and (for a review) which rule it broke.
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.
- 1mo ago First seen · 47 lines · 56 tokens per session scan A 963612ba82e3
ux-copy is an agent published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 564 once invoked, about $0.0002 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 2026-09-21.
ux-copy compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-copyikhanux/ai-coding-blueprint | Agent | 2 | 1mo ago | MIT | A | 56 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | yesterday | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 631 | yesterday | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 15d ago | none | A | 52 | Claude Code |