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 eugenelim/agent-ready-repo --skill css-architecturegit clone --depth 1 https://github.com/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/css-architecture)<a href="https://agentmods.dev/skills/eugenelim/agent-ready-repo/css-architecture"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/css-architecture/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/eugenelim/agent-ready-repo/css-architecture"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/css-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Prompt Injection · line 248 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Prompt Injection · line 48 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00074 | $0.02697 |
| Opus 5 | $0.00037 | $0.01349 |
| Sonnet 5 | $0.00015 | $0.00539 |
| Haiku 4.5 | $0.00007 | $0.00270 |
Grade A, and why
css-architecture 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 5d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: css-architecture
Load this skill when setting up CSS architecture for a new codebase, or
auditing and refactoring CSS in an existing one where specificity conflicts,
hard-to-predict cascade behavior, or unsafe deletion are active problems.
Do not load it for routine component styling on a codebase that already has
a working architecture. Load css-architecture when:
- Starting a new project and deciding the CSS organization strategy
- A codebase has accumulated specificity conflicts that produce unpredictable cascades
- Engineers cannot safely delete a CSS rule because they don't know what will break
- The codebase has grown beyond one developer and CSS changes produce unexpected regressions
Cascade layers
@layer (Cascade Layers) is Baseline Widely Available as of 2022. It makes
the cascade explicit and controllable: a rule in a higher layer always wins
over a rule in a lower layer, regardless of specificity.
Canonical layer order:
/* Declare all layers upfront — this is the only place layer order is defined */
@layer reset, base, theme, components, utilities, overrides;
| Layer | Contents | Notes |
|---|---|---|
reset |
Browser default reset (e.g., box-sizing, margins) | No project-specific styles |
base |
HTML element defaults (body font, heading scale, link style) | Unclassed element selectors only |
theme |
Design token custom properties (:root {} token block) |
No component styles |
components |
Component class selectors (.btn, .card, .modal) |
The main application CSS lives here |
utilities |
Single-purpose utility classes (hidden, sr-only, spacing helpers) |
High-frequency reuse; should have low specificity |
overrides |
Escape hatch for third-party library overrides, print styles | Rarely used; document every rule added here |
Why ordering is the invariant: a rule in utilities always beats a rule
in components, regardless of how specific the component rule is. This means
utilities are reliable (you can always use a utility to override a component
style), but components cannot override utilities. The layer order must be
declared once at the top of the main stylesheet — never redeclare it in
component files.
What ships with it
1 file 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.
- 5d ago Changed · +35 tokens per session 1cd449a26cb0
- 6d ago First seen · 266 lines · 39 tokens per session scan A 8f5cea415caa
css-architecture is a skill published in the GitHub repository eugenelim/agent-ready-repo (20 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 2,697 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 2026-09-03.
Other skills, from other repositories
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
mobile-styling-nativewind
NativeWind v4+ - Tailwind CSS utility classes for React Native, className prop, CSS variables, dark mode, platform prefixes, animations, theming, third-party component integration.
shared-tooling-biome
Biome v2 unified linter, formatter, and import organizer — single Rust-powered tool replacing ESLint + Prettier with 97% Prettier compatibility and 20x faster performance.
mobile-styling-unistyles
Unistyles 3.0 styling - C++ powered StyleSheet superset with zero re-renders, theming, breakpoints, variants, dynamic functions, runtime values.
mobile-ui-components-tamagui
Tamagui universal UI - styled(), tokens, themes, optimizing compiler, responsive media queries, animations, Sheet/Dialog components.