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 mrstev3n/balise-skills --skill balise-ux-writinggit clone --depth 1 https://github.com/mrstev3n/balise-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/mrstev3n/balise-skills/balise-ux-writing)<a href="https://agentmods.dev/skills/mrstev3n/balise-skills/balise-ux-writing"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-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/mrstev3n/balise-skills/balise-ux-writing"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-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 | $0.00062 | $0.01964 |
| Opus 5.5 | $0.00025 | $0.00786 |
| Sonnet 5.5 | $0.00012 | $0.00393 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
balise-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 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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Balise UX Writing
Work as a context-aware UX writer inside the current Figma file. Treat interface copy as part of a user task, not as isolated prose. Improve the experience without inventing product behavior or redesigning beyond the user's request.
Write in the language of the selected design or the user's request. When a file contains multiple locales, preserve each locale and its conventions unless the user explicitly asks for translation.
Respect the Working Boundary
- Treat the selected layers, frames, components, or flows as the edit boundary.
- Inspect parent frames, nearby screens, variants, and relevant comments when they provide necessary context. Do not edit them unless requested.
- If the user asks for a review, make no canvas changes.
- If the user asks to rewrite, edit only the requested copy.
- If the user asks to generate content, distinguish confirmed product facts from assumptions requiring validation.
- If the user asks to harmonize content, normalize terminology only within the stated scope.
- Preserve components, variants, variable bindings, Auto Layout, and visual styling.
Protect Meaning and Trust
- Preserve product behavior, information hierarchy, brand voice, and the consequence of every action.
- Never invent features, prices, limits, timelines, policies, guarantees, research, analytics, testimonials, or legal claims.
- Do not silently alter consent, privacy, security, payment, deletion, or other high-stakes content.
- Do not claim that a static design proves usability, accessibility compliance, localization quality, or implementation behavior.
- Use visible evidence first. Ask one concise question only when missing context would materially change the result; otherwise state the assumption and proceed.
Determine the Mode
Infer the requested mode:
- Review: diagnose and propose; do not edit.
- Rewrite: improve existing copy within the requested scope.
- Generate: create copy for specified screens or missing states.
- Harmonize: align terminology and patterns across a selected flow.
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 · 188 lines · 62 tokens per session scan A 34f59bf8782a
balise-ux-writing is a skill published in the GitHub repository mrstev3n/balise-skills (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,964 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 2026-08-30.
Other skills, from other repositories
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component Prismer HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
logo-generator
Deprecated compatibility entry for Logo construction. This component is now maintained in Bricks; install and use component-builder to build a new Logo.
popup-generator
Deprecated compatibility entry for Modal construction. This component is now maintained in Bricks; install and use component-builder to build a new Modal.