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.
npx agentmods add skills/fusengine/agents/ux-copynpx skills add fusengine/agents --skill ux-copygit clone --depth 1 https://github.com/fusengine/agentsWrote 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/skills/fusengine/agents/ux-copy)<a href="https://agentmods.dev/skills/fusengine/agents/ux-copy"><img src="https://agentmods.dev/badge/skills/fusengine/agents/ux-copy.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.02291 |
| Opus 5 | $0.00015 | $0.01145 |
| Sonnet 5 | $0.00006 | $0.00458 |
| Haiku 4.5 | $0.00003 | $0.00229 |
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 yesterday.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runs 10 mechanical ban-lists: filler verbs/hype adjectives, slop placeholder names, fake-precise numbers, unjustified Title Case headlines, humor in error copy ("Oops!"), the AI production-tell catalogue, em-dash-as-crutch, "Not X. Y." manufactured contrast, the "theater" keyword, and all-caps body copy.
Enforces one copy register per page (brand traces to the POV, product stays domain-specific). Judgment calls that aren't mechanically resolvable are quoted, located, and routed to design-review's challenger gate — never self-scored.
UX Copy — Self-Audit + Ban-Lists, One Register Per Page
When
Any time visible copy is written or edited — headlines, subheads, eyebrows, button
labels, body, captions, alt text, error messages, empty states — inside generate/
critique/audit/polish (design-method) or as a standalone copy pass. Register is
resolved once, at Gate 0 (design-method/SKILL.md), before this runs — never re-guessed
here.
Input
- Register (
brand/product) from Gate 0. - Sector, if resolved, for
references/voice-tone-sectors.md. - Every visible string in the deliverable.
One register per page — hard rule
A single copy register per page (references/copy-self-audit.md §7): don't mix
technical mono, editorial prose, and marketing punch on one surface unless the brand
voice explicitly calls for it. Register direction is conditional exactly like layout and
motion (design-method/references/register/copy.md §3): brand copy must trace to
the one-sentence POV — run the Competitor Lift Test on the paragraph itself, could it run
unchanged on a competitor's site; product copy stays precise and domain-specific,
naming the real object and the real action, never marketing voice bleeding into the app
shell.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/copy-ecommerce.md 2.9 KB
- references/copy-fintech.md 3.0 KB
- references/copy-saas.md 3.0 KB
- references/copy-self-audit.md 5.7 KB
- references/empty-states-copy.md 5.6 KB
- references/microcopy-patterns.md 3.8 KB
- references/templates/copy-guide-template.md 3.4 KB
- references/templates/cta-patterns.md 2.0 KB
- references/templates/error-messages.md 2.6 KB
- references/templates/onboarding-copy.md 2.3 KB
- references/voice-tone-sectors.md 5.0 KB
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.
- yesterday First seen · 141 lines · 31 tokens per session scan A 26471a40edc6
ux-copy is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 2,291 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 2026-09-03.
Other skills, from other repositories
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks…
radin-doctor
Check that radin's own install under /.claude is complete and its optional companion tools are reachable. Use for /radin-doctor, "check my radin install", "is radin installed correctly", "radin doctor", "verify radin install".
designing-interfaces
Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or extracting patterns from existing code.
managing-product
Extracts product requirements and produces a PRD. Use when a user wants to build software and needs to define what to build before architecture or implementation, when scoping an MVP, or when translating a vague idea into a buildable specification.
orchestrating-software-dev
Runs software development projects from idea to completion. Use when starting a software project, adding a feature, fixing a bug, or resuming an in-progress build.
collecting-sources
Collects research sources with quality evaluation. Use when gathering or finding sources, building a source library, searching for academic papers, or performing RADAR assessment.