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 skills/jinning6/noosphere/frontend-layering-specificity-debugnpx skills add JinNing6/Noosphere --skill frontend-layering-specificity-debuggit clone --depth 1 https://github.com/JinNing6/NoosphereWrote 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/jinning6/noosphere/frontend-layering-specificity-debug)<a href="https://agentmods.dev/skills/jinning6/noosphere/frontend-layering-specificity-debug"><img src="https://agentmods.dev/badge/skills/jinning6/noosphere/frontend-layering-specificity-debug.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 5.1 | $0.00069 | $0.00666 |
| Opus 5 | $0.00034 | $0.00333 |
| Sonnet 5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
frontend-layering-specificity-debug 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Layering And Specificity Debug
Diagnose Before Styling
- Reproduce at the reported viewport and interaction state.
- Record bounding boxes plus computed
font-size,line-height,width,height, andz-index. - Compare equivalent element types. A
<button>and an<a>that share a component class but render differently usually indicate a selector or user-agent boundary. - Enumerate matched CSS rules instead of inferring from source order alone.
- Use
document.elementFromPoint()at the overlap to identify the element that actually paints or receives input.
Fix Typography Specificity
- Treat shorthand declarations such as
font: inheritas resettingfont-size,font-weight, andline-heighttogether. - Check specificity as well as order.
.app buttonoverrides.buttoneven when.buttonappears later. - In scoped resets, prefer
font-family: inheritand explicit inherited properties. Keep component-levelfont-sizeandline-heightauthoritative. - Add
white-space: nowraponly to stable command controls; use responsive label collapse when the toolbar cannot fit. - Verify computed styles on real
<button>,<a>,<input>, and<select>elements after the fix.
Fix Projected 3D Labels
- Remember that Drei
<Html>is projected DOM, not canvas pixels. Its defaultzIndexRangeis extremely high and can paint over an otherwise opaque drawer. - Assign a bounded range such as
zIndexRange={[8, 1]}for scene labels, then keep application chrome above it. - Do not keep increasing drawer z-index without identifying the projected label range and stacking context.
- Reserve real canvas width for persistent desktop drawers when labels or selected nodes would otherwise sit underneath them.
- Use semantic zoom: show detailed labels only for hover, selection, a focused domain, or an actual non-empty search match.
Regression Checks
Run desktop, compressed desktop, and mobile checks:
const style = getComputedStyle(control)
expect(style.fontSize).toBe('13px')
expect(document.body.scrollWidth).toBe(document.documentElement.clientWidth)
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 First seen · 60 lines · 69 tokens per session scan A 1c3675899430
frontend-layering-specificity-debug is a skill published in the GitHub repository JinNing6/Noosphere (18 stars, last pushed 5d ago), licensed Apache-2.0. It adds 69 tokens to every session and 666 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
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Accessibility Audit Helper
Reviews UI code and components for WCAG 2.1 accessibility violations and provides specific fixes.
React Component Reviewer
Analyzes React components for performance, accessibility, and modern hook usage.
senior-frontend
Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
react-native-expert
Build, optimize, and debug cross-platform mobile applications with React Native and Expo. Use when the user needs navigation setup, native-module integration, mobile performance work, or platform-specific iOS and Android handling.
prjct
The agentic harness for AI coding agents: machine-verified ships, guarded edits, and project lookup that beats re-deriving from source. Run the prjct verb yourself; use prjct work normally.