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 keodubo/PAW-Wiki --skill paw-frontend-layergit clone --depth 1 https://github.com/keodubo/PAW-WikiWrote 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/keodubo/paw-wiki/paw-frontend-layer)<a href="https://agentmods.dev/skills/keodubo/paw-wiki/paw-frontend-layer"><img src="https://agentmods.dev/badge/skills/keodubo/paw-wiki/paw-frontend-layer/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/keodubo/paw-wiki/paw-frontend-layer"><img src="https://agentmods.dev/badge/skills/keodubo/paw-wiki/paw-frontend-layer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.01151 |
| Opus 5 | $0.00030 | $0.00575 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
paw-frontend-layer 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paw Frontend Layer
Overview
Use this for the TP final frontend/ SPA source after $paw-tp-final-migration has confirmed the stage and slice. Keep the frontend as a client of the REST API: UI and state live here, business authority stays in backend services, and HTTP contracts stay explicit.
Read references/frontend-rules.md before editing frontend source, tests, or build config.
Required First Pass
- Confirm the current TP final vertical slice from
$paw-tp-final-migration. - Inspect
frontend/package.json, lockfile, build config (vite.config.*, Angular/React equivalent), router, API client/services, stores/composables, i18n catalogs, tests, and the webapp packaging config that consumes the build output. - Identify the API contract the slice consumes: resource URIs, media types,
Location,Link,ETag, auth headers, Problem Details, and exposed CORS headers. - State the frontend runner/build commands from package scripts. If no runner exists, define a repeatable smoke check before claiming the slice is verified.
- Do not choose or replace a frontend framework unless the user asked or the repo already makes the choice clear.
Workflow
- Stay inside the current user-visible slice: one SPA route/flow, its API calls, state, forms, errors, i18n, tests, and smoke gate.
- Put HTTP details in an API client/service boundary. Components should not scatter raw
fetch/axios, token refresh, header parsing, or URL construction. - Keep routes URL-driven: refresh, deep links, filters, pagination, back/forward, and bookmarks must work under the WAR context path.
- Use stores/composables for shared state and async logic. For HATEOAS-heavy flows, use cache by URI, identity map behavior, request coalescing, and
ETagrevalidation where the API supports it. - Treat client validation as UX only. Map backend validation and Problem Details into user-visible errors without hiding backend authority.
- Keep i18n catalogs complete across supported locales; use full messages with placeholders, not concatenated fragments.
- Test public behavior: route state, rendered user outcomes, form validation, store/composable state transitions, API error handling, i18n output, and cache/refetch behavior.
- Run frontend tests/build through declared package scripts, then the Maven/WAR gate when packaging, base path, static hosting, or assets are touched.
What ships with it
2 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.
- 11d ago First seen · 80 lines · 59 tokens per session scan A a82b0522bdf3
paw-frontend-layer is a skill published in the GitHub repository keodubo/PAW-Wiki (10 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,151 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 2026-08-31.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…