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 agentmods add instructions/williamisnotdefined/rubiks-cube-solver/frontend-stylinggit clone --depth 1 https://github.com/williamisnotdefined/rubiks-cube-solverWrote 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/instructions/williamisnotdefined/rubiks-cube-solver/frontend-styling)<a href="https://agentmods.dev/instructions/williamisnotdefined/rubiks-cube-solver/frontend-styling"><img src="https://agentmods.dev/badge/instructions/williamisnotdefined/rubiks-cube-solver/frontend-styling.svg" alt="Measured on agentmods" 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 | $0.01942 | $0.01942 |
| Opus 5 | $0.00971 | $0.00971 |
| Sonnet 5 | $0.00388 | $0.00388 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
rubiks-cube-solver frontend-styling.instructions.md 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 4d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated from ai/registry.json. Do not edit manually.
Canonical skill: ../../ai/skills/frontend-styling.md.
Referenced context:
../../ai/rules/frontend-rules.md../../ai/rules/frontend-styling-rules.md../../ai/rules/frontend-quality-rules.md
This file is compiled from canonical AI knowledge files. Edit canonical files under ai, then run npm run ai:sync.
Compiled AI Skill: frontend-styling
Canonical Skill: ai/skills/frontend-styling.md
Frontend Styling
Use for Tailwind utilities, theme tokens, responsive layout, and visual treatment.
Read First
ai/rules/frontend-rules.mdai/rules/frontend-styling-rules.mdai/rules/frontend-quality-rules.md
Workflow
- Follow nearby shadcn-compatible UI patterns and semantic tokens in the single CSS entrypoint.
- Use static class strings when possible, the existing
cnhelper for shared primitives/class merging, and establishedclassnamesusage in feature code when merge semantics are unnecessary. - Check focus, reduced motion, themes, mobile layout, and visualization sizing.
- Run
npm run theme-colors:check, web build, and lint.
Referenced Context
Reference: ai/rules/frontend-rules.md
Frontend Rules
Boundaries
- Keep solving, notation semantics, puzzle validity, and replay verification in Rust. React renders and coordinates typed product workflows.
- Keep HTTP mechanics and normalization in
apps/web/src/api; UI consumes domain hooks/adapters. - Typed scan-session contracts MAY contain reviewed stickers, confidence, and manual overrides. Notation solve UI MUST NOT expose facelet, Kociemba, or raw cube-state inputs.
- Keep API load, form, page workflow, solve result, scanner review, and visualization playback state separately owned unless a focused page owner coordinates them.
- Use the active
@rubiks-cube-solver/rubiks-cubepackage as a visualization adapter, never as canonical solver state.
Web Runtime And Locales
- Preserve static rendering for indexable routes,
hydrateRootfor generated markup, and SPA navigation after hydration. - Keep
en-UScanonical without a prefix. Publish/index any of the nine supported locales only when its visible and SEO content is fully translated with placeholder parity. - Treat route slugs as stable identifiers. They need not be English and MUST NOT vary by locale; slug changes require redirects and canonical planning.
- Keep route/page code in its bounded context and shared code behind a demonstrated cross-context consumer.
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.
- 4d ago First seen · 128 lines · 1,942 tokens per session scan A 2d4602dc2b41
rubiks-cube-solver frontend-styling.instructions.md is an instructions file published in the GitHub repository williamisnotdefined/rubiks-cube-solver (4 stars, last pushed 11d ago), licensed MIT. It adds 1,942 tokens to every session, about $0.0097 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 2026-08-31.
Other instructions, from other repositories
weapp-tailwindcss CLAUDE.md
Claude Code instructions for sonofmagic/weapp-tailwindcss, covering claude.md, project overview, monorepo structure, common development commands and build.
screenshot-to-code CLAUDE.md
Instructions for abi/screenshot-to-code, a project described as: Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue).
shadcn-htmx AGENTS.md
Instructions for productdevbook/shadcn-htmx, covering agent guide, hard rules, what's vendored, and when to read each, repos/htmx/ — htmx v4 source (branch: four-dev) and repos/tailwindcss/ — tailwind css v4 source (branch: main).
tidyfactor-design AGENTS.md
Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).
app.spectrum.analyzer css.instructions.md
Instructions for polarity/app.spectrum.analyzer, a project described as: Spectrum Analyzer for the Browser.
fern-marketing-site-template AGENTS.md
AGENTS.md instructions for fern-api/fern-marketing-site-template, covering agents.md, authoring rules, 1. design tokens, not raw values, 2. use cn() for conditional classes and 3. every page exports metadata; url structure is sacred.