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 joao-aires/agent-skills-public --skill ux-writinggit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/ux-writing)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/ux-writing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ux-writing/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/joao-aires/agent-skills-public/ux-writing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ux-writing.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 | $0.00051 | $0.00626 |
| Opus 5.5 | $0.00020 | $0.00250 |
| Sonnet 5.5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
ux-writing 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write interface copy for the actual task
Make the action, current state and consequences understandable in the product's voice. Use interaction design for behavior and interface quality for rendered fit.
Ground language in behavior
Read the whole affected flow, adjacent states and established vocabulary. Identify the reader's goal, what the system permits and knows, the stakes and the available next action. Separate UI text from sample data and annotations. Resolve technical facts from contracts/code; ask about unresolved product decisions that change meaning.
Match every recommended message, including the preferred default, to authoritative state and supported behavior.
- Distinguish an acknowledged request, work in progress and confirmed outcome.
- Recovery, notification, timing and download promises require a real contract.
- Preserve material consequences of consent, payment, security, sharing and deletion; a copy change cannot redefine permissions or recovery.
Make decisions and recovery clear
Name the action by what happens to the user's object, using the same term before and after the action. A label should let the user predict the result without needing to understand the implementation. Keep field labels visible when values have been entered, and make destinations clear enough that navigation does not depend on surrounding decoration.
Review consequential confirmations as a whole. The title, explanation and actions should identify the affected object, what will happen, and any material consequence such as loss of access or irreversibility when established. Remove repetition that competes with that decision, while retaining information the user needs to choose safely. Supply complete localized replacements with their placeholders intact.
Distinguish validation, connectivity, denied authority and system failure. Explain the affected outcome and an available recovery action; preserve input where retry is supported. Give first use, no matches, loading, partial and unavailable data meanings suited to the task. Clarity should preserve the accepted brand voice.
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 Changed · +10 lines dadb6e74b87f
- 3d ago Changed a12acc89947d
- 5d ago First seen · 34 lines · 51 tokens per session scan A e72a31119939
ux-writing is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 626 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 2026-10-17.
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 $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.