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-visual-referencesgit 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-visual-references)<a href="https://agentmods.dev/skills/mrstev3n/balise-skills/balise-visual-references"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-visual-references/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-visual-references"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-visual-references.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 | $0.00078 | $0.02068 |
| Opus 5 | $0.00039 | $0.01034 |
| Sonnet 5 | $0.00016 | $0.00414 |
| Haiku 4.5 | $0.00008 | $0.00207 |
Grade A, and why
balise-visual-references 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual References for Figma
Guide the user from a design question to a useful reference set, then translate the selected examples into original design decisions. Work entirely from this file and from material the user supplies. Do not assume access to a browser, external connector, MCP, API, or private reference library.
Operating rule
Separate the workflow into two phases:
- Recommend and collect: propose sources, search terms, and capture instructions; ask the user to visit the sources and attach selected screenshots or links.
- Analyze and apply: inspect only the material supplied in the conversation or available in the Figma file, then derive principles for the current design.
Do not describe a source or reference as inspected until its visual content is actually available. A URL alone may identify provenance but does not prove the current visual state of the page.
Frame the request
Identify:
- the deliverable: website, mobile app, desktop product, dashboard, brand system, deck, campaign, email, or another surface;
- the target pattern: app bar, navigation, hero, cards, table, form, onboarding, pricing, search, settings, empty state, motion, typography, or another reusable problem;
- the desired granularity: system, page, section, screen, component, flow, interaction, or asset;
- the project context: audience, market, industry, tone, device, content density, accessibility, and technical constraints;
- the decision the references should clarify.
If essential context is missing, ask at most one concise question before recommending sources.
Recommend a focused route
Choose three to five complementary sources. Favor specialist libraries over general inspiration feeds. For each recommendation, include:
| Source | Why it fits | Starting URL | Search terms or route | What to capture |
|---|
Use precise queries that combine the product, component, state, and context. Examples:
mobile banking bottom navigation active stateB2B SaaS data table bulk actionseditorial mobile app bar scroll behavioronboarding permission request before afterpricing comparison enterprise SaaSempty state no results filters dashboard
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 · 139 lines · 78 tokens per session scan A 3370333fc372
balise-visual-references is a skill published in the GitHub repository mrstev3n/balise-skills (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,068 once invoked, about $0.0004 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…
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…
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…