Borrowing it
Nothing to install: this file belongs to yusifeng/formax. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yusifeng/formax/main/.codex/skills/formax-web-style-system/SKILL.mdgit clone --depth 1 https://github.com/yusifeng/formaxWrote 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/yusifeng/formax/formax-web-style-system)<a href="https://agentmods.dev/skills/yusifeng/formax/formax-web-style-system"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-web-style-system/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/yusifeng/formax/formax-web-style-system"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-web-style-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 41 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00056 | $0.00750 |
| Opus 5 | $0.00028 | $0.00375 |
| Sonnet 5 | $0.00011 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
formax-web-style-system 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 10d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Formax Web Style System
Goal
Apply a business-agnostic visual style system for web interfaces.
Enforce a calm, desktop-grade aesthetic with strong readability, token-first styling, and clear interaction hierarchy.
Do not introduce product workflow assumptions, domain copy assumptions, or business IA decisions.
Trigger Contract
Use this skill by default for all frontend and web UI tasks.
If the task is not frontend/UI work, do not apply this skill.
If the repository or task provides an existing design system, brand guide, or component library:
- Follow the existing system first.
- Use this skill only to harmonize tone, spacing rhythm, and state clarity.
- Never override explicit local design constraints.
Workflow
- Read
references/style-doctrine.mdfirst to lock the visual direction. - Read
references/token-blueprint.mdto define CSS variable layers before proposing UI details. - Read
references/layout-patterns.mdwhen composing desktop layout, density, and responsive fallback. - Read
references/component-tone.mdwhen styling components, states, and interaction emphasis. - Read
references/anti-patterns.mdas a final rejection checklist before returning output. - Apply all
CRITICAL STYLE OVERRIDESfrom the references as mandatory constraints.
For small styling requests, keep output concise but still include token strategy and state clarity.
Formax Overrides (Mandatory for CSS Rework)
When the task touches CSS in packages/web-reference-react/**, do this before editing:
- Read
.codex/skills/formax-web-css-convergence-workflow/SKILL.md. - Lock a pre-edit intake contract (target model, non-goals, ownership boundary, acceptance checks).
- Use single-axis passes (geometry -> color -> interaction), avoid mixed multi-axis edits.
- Validate with:
bun run test -- src/App.test.tsx(inpackages/web-reference-react)
- If and only if the task includes transparency/window layering:
- Read
docs/contracts/web/window-transparency-construct.md - Run
bun run test:e2e -- e2e/window-transparency.evidence.spec.js --project=chromium(inpackages/web-reference-react)
- Read
What ships with it
5 files 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.
- 10d ago First seen · 84 lines · 56 tokens per session scan A 478eaf28b068
formax-web-style-system is a skill published in the GitHub repository yusifeng/formax (193 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 750 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
frontend-taste
Premium frontend design skills that override LLM defaults. Prevents generic 'AI-looking' UI. Enforces deterministic typography, calibrated color, asymmetric layouts, spring physics, hardware-accelerated motion. Triggers: 'UI tasarla', 'design a UI', 'premium landing page', 'frontend taste', 'anti-slop', 'dashboard…
design-tokens
Project-level DESIGN.md tokens reference. When the project has a DESIGN.md file, agents producing UI / components / visuals must consult this skill to use canonical color/typography/spacing tokens rather than inventing new ones. Triggers on: UI generation, component creation, design brief, visual asset, tailwind…
ui-audit
Audit UI for design token compliance and component adoption. Static grep-based analysis against the sitemap's page and component files. Requires a design system with semantic tokens.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
visual-audit
Visual audit - typography, spacing, colour discipline, dark-mode polish, info density. Scores pages on 10 aesthetic dimensions via Playwright screenshots.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.