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-css-convergence-workflow/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-css-convergence-workflow)<a href="https://agentmods.dev/skills/yusifeng/formax/formax-web-css-convergence-workflow"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-web-css-convergence-workflow.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00902 |
| Opus 5 | $0.00017 | $0.00451 |
| Sonnet 5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
formax-web-css-convergence-workflow 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 8d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
formax-web-css-convergence-workflow
Goal
- Prevent repeated CSS rework by locking requirements before any style edits.
- Convert ambiguous visual requests into a concrete edit contract with explicit acceptance checks.
- Keep behavior stable while converging structure, naming, and styling.
Use this skill when the task involves:
- component styling or layout adjustments
- cross-file CSS + TSX class changes
- interaction visual states (hover/active/focus/selected)
- repeated back-and-forth UI tuning that needs convergence
Intake Contract (Run Before Editing)
- Require this 8-line input contract (fill missing items by explicit assumptions, not guesswork):
- Target model in one sentence (final visual geometry).
- Non-goals / do-not-touch list.
- State model (if any) and single source of truth.
- Ownership boundary (main process vs renderer).
- Acceptance criteria (what must be true, what must never appear).
- Runtime matrix (command, platform, light/dark).
- Iteration policy (single-axis change per pass).
- Rollback point (which commit/file set is safe fallback).
Where to change what
- Core styling surfaces:
packages/web-reference-react/src/styles.csspackages/web-reference-react/src/css/theme.css
- Core UI wiring:
packages/web-reference-react/src/app/ui/AppShell.tsxpackages/web-reference-react/src/components/LeftRail.tsxpackages/web-reference-react/src/components/left-rail/SidebarItem.tsx
- Browser bridge typing surface (when needed):
packages/web-reference-react/src/vite-env.d.ts
- Desktop main/preload ownership (only for stateful window-level visuals):
packages/desktop-electron/src/main.tspackages/desktop-electron/src/preload.tspackages/desktop-electron/src/windowAppearanceState.ts
- Scenario-specific construct (read only if task touches transparency):
docs/contracts/web/window-transparency-construct.md
Patterns
- Freeze-Then-Edit Pattern
- Restate final model first.
- Freeze non-goals (do not touch drag region, menu entries, unrelated text/copy).
- Only then open code.
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.
- 8d ago First seen · 90 lines · 35 tokens per session scan A ef35bc8c951f
formax-web-css-convergence-workflow is a skill published in the GitHub repository yusifeng/formax (193 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 902 once invoked, about $0.0002 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
threejs
Build immersive 3D web experiences with Three.js - WebGL/WebGPU library for scenes, cameras, geometries, materials, lights, animations, loaders, post-processing, shaders (including node-based TSL), compute, physics, VR/XR, and advanced rendering. Use when creating 3D visualizations, games, interactive graphics, data…
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…
responsive-audit
Responsive audit: test pages at 375/768/1024px breakpoints via Playwright. Checks overflow, tap targets, sidebar collapse, text reflow, WCAG 1.4.4 zoom.
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.
image-taste-frontend
Elite frontend image-direction skill for generating premium, artistic, implementation-friendly website design references. Uses combinatorial variation to avoid repetitive AI aesthetics, enforces cinematic hero minimalism, strong hierarchy, generous spacing, image-led composition, and anti-slop visual discipline. For…