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-ui-statesgit 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-ui-states)<a href="https://agentmods.dev/skills/mrstev3n/balise-skills/balise-ui-states"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-ui-states/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-ui-states"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-ui-states.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 | $0.00069 | $0.02584 |
| Opus 5 | $0.00034 | $0.01292 |
| Sonnet 5 | $0.00014 | $0.00517 |
| Haiku 4.5 | $0.00007 | $0.00258 |
Grade A, and why
balise-ui-states 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 12d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI States
Complete the state system around selected Figma screens, components, or flows. Do not generate a universal gallery. Choose only states that are plausible, consequential, and not already covered.
Treat every state as part of a flow with a trigger, preserved context, exit, recovery, and next state.
Core rules
- Preserve source frames and components unless the user explicitly asks to edit them.
- Work inside the user’s selection and its necessary adjacent flow. Do not redesign unrelated screens.
- Inspect existing components, variants, variables, styles, copy, prototype links, annotations, and naming before creating anything.
- Reuse the product’s visual language and component system. Do not create a parallel design system.
- Do not invent API behavior, permissions, timings, progress percentages, persistence guarantees, or recovery rules as facts.
- Label observed, created, prototype-verified, proposed, and unknown behavior separately.
- Prefer the smallest affected region. A component-level update should not become a full-page loading screen.
- Preserve user input and valid data through errors whenever the product model permits it.
- Never disguise an error, access restriction, or loading failure as a friendly empty state.
- Do not claim accessibility or production behavior from a static frame alone.
Infer the mode
- Audit: inventory existing states and prioritize gaps without editing.
- Design: create the relevant proposed states on labeled copies.
- Repair: correct incomplete, misleading, inaccessible, or dead-end states.
- Complete: audit, create or repair, connect what can be prototyped, and report evidence.
If the request is ambiguous, default to Audit. If the user asks to add, complete, fix, or design states, use Complete.
Workflow
1. Frame the product moment
Identify from the selection and surrounding canvas:
- the screen, component, control, or flow being evaluated;
- the user goal and value of the ideal state;
- the screens or actions immediately before and after it;
- visible data sources, user input, permissions, network work, and persistence;
- the question the prototype or matrix should answer;
- the intended audience: design review, product decision, engineering handoff, or usability test.
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.
- 12d ago First seen · 297 lines · 69 tokens per session scan A 380a57322a5a
balise-ui-states is a skill published in the GitHub repository mrstev3n/balise-skills (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 69 tokens to every session and 2,584 once invoked, about $0.0003 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
ijfw-ui-spec
Use when the user says: 'ui spec', 'design contract', 'ui audit setup', 'lock the design', 'visual contract', 'ui review setup', or '/ijfw-ui-spec'. Produces UI-SPEC.md as the visual design contract before any frontend or visual-artifact build, and dispatches ijfw-ui-auditor as the final 6-pillar gate.
ijfw-design
Use when the user says: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look better', 'polish', 'pretty', 'professional', 'user experience', 'layout', 'visual', 'accessibility', 'colors', 'typography', 'brand'.
Add Claude design-system and accessibility workflows with UX/UI Agent Skills
Use UX/UI Agent Skills when Claude should generate tokens, component specs, accessibility audits, and framework-specific UI code from a repeatable design workflow.
design-maker
name: design-maker description: Used when the Design Brief is complete and the user needs to generate mockups. Reads Product-Spec.md and Design-Brief.md, then generates a complete set of design deliverables through a design tool MCP, including all pages, state variants, component specifications, design tokens…
ui-designer
Designs and builds interface work on top of the design system the repo already has: layout, spacing, hierarchy, interaction states, and accessible defaults, with creativity calibrated to the surface instead of an unrequested redesign. Use when asked for a new screen, a redesign, empty, loading, and error states, or to…
design-brief-builder
name: design-brief-builder description: Used when the user wants to define a design style or visual direction, or says something vague like 'I want a premium/sleek/modern look'. Guides the user through a design interview to clarify visual preferences and outputs Design-Brief.md. After Brief is saved, MUST run Next…