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 skills add tushaarmehtaa/tushar-skills --skill ui-copygit clone --depth 1 https://github.com/tushaarmehtaa/tushar-skillsWrote 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/tushaarmehtaa/tushar-skills/ui-copy)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/ui-copy"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/ui-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/skills/tushaarmehtaa/tushar-skills/ui-copy"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/ui-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01244 |
| Opus 5 | $0.00018 | $0.00622 |
| Sonnet 5 | $0.00007 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
ui-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 11d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI copy
Write interface language that tells people what state they are in, what changed, what is safe, and what they can do next. Match wording to actual product behavior and let tone vary appropriately with consequence.
Choose mode and scope
- Audit — inventory and diagnose copy without editing unless asked.
- Flow rewrite — repair one journey across all states and channels.
- Generate — create a copy specification for new screens or behavior.
- Implement — update source strings, localization resources, or content models and verify the running product.
Define in-scope surfaces, routes, flows, locales, channels, and states. For broad work, sample low-risk routine interactions and high-risk account, permission, payment, privacy, and destructive flows before expanding coverage.
Inspect the codebase and product evidence before asking questions. Recover the primary user, domain terminology, existing voice, product behavior, localization setup, content ownership, and design constraints. Ask only for unresolved product decisions or voice choices that materially alter the copy.
Read copy quality and state rules before the final writing pass or whenever errors, progress, localization, destructive actions, or voice consistency are in scope.
Build a copy manifest
Search components, route data, constants, locale files, CMS fixtures, server responses, form schemas, validation, toasts, notifications, emails, dialogs, empty states, accessible labels, and alt text.
Record each material source decision:
Surface/channel and flow:
Route/component and source location:
State and audience:
Rendered text:
Message ID, locale, variables, plural/select branches, fallback:
Actual system behavior or destination:
Claim/cause provenance when consequential:
Distinguish unique source strings from rendered instances. Exclude tests, logs, and non-user-facing examples unless the request includes documentation copy.
Model meaningful states
What ships with it
1 file 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.
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.
- 11d ago First seen · 127 lines · 36 tokens per session scan A 792fb37bb249
ui-copy is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (11 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,244 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.