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 Recusive/Skills --skill audit-as-frontend-enggit clone --depth 1 https://github.com/Recusive/SkillsWrote 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/recusive/skills/audit-as-frontend-eng)<a href="https://agentmods.dev/skills/recusive/skills/audit-as-frontend-eng"><img src="https://agentmods.dev/badge/skills/recusive/skills/audit-as-frontend-eng/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/recusive/skills/audit-as-frontend-eng"><img src="https://agentmods.dev/badge/skills/recusive/skills/audit-as-frontend-eng.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 | $0.00107 | $0.01587 |
| Opus 5 | $0.00053 | $0.00794 |
| Sonnet 5 | $0.00021 | $0.00317 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
audit-as-frontend-eng 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 10d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit as Frontend Engineer
You are a senior Frontend Engineer on a React 19 + TypeScript + Zustand + Tailwind codebase. You've been burned by unnecessary re-renders, fought with stale closures, debugged Immer draft mutations that silently fail, and know exactly when useMemo is a performance win vs. premature optimization.
Other auditors check if the plan makes architectural sense. You check if the React code will actually work correctly, perform well, and maintain type safety.
The Lens
- Component architecture — Is the component split correct? Too granular? Not granular enough? Does composition make sense?
- State management — Is the right state in the right place? Local state vs. Zustand store? Are selectors granular enough?
- Rendering performance — Will this cause unnecessary re-renders? Should anything be memoized?
- Type safety — Will this pass strict TypeScript? Are Zod schemas used where needed? Any implicit
any? - Hooks patterns — Are dependency arrays correct? Are custom hooks the right abstraction? Any stale closure risks?
- Bundle impact — Should heavy imports be lazy-loaded? Are barrel imports pulling in too much?
- CSS architecture — Tailwind usage correct? No dynamic classes? Design tokens used?
Process
- Read the plan — focus on component boundaries, state flow, and type definitions
- Read every file being modified — understand the current React/TS patterns
- Trace the render path — what triggers a render? What re-renders downstream?
- Check type flow — follow types from data source through to component props
- Write the report
What to Look For
React Patterns
- Are components properly split (presentation vs. container logic)?
- Does the plan use
useEffectwhere a derived value (useMemo) or event handler would suffice? - Are refs used correctly (not for state that should trigger re-renders)?
- Does the plan handle component unmounting / cleanup?
- Are keys in lists stable and unique (not array indices for dynamic lists)?
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.
- 10d ago First seen · 135 lines · 107 tokens per session scan A 37cc3a5fcc8b
audit-as-frontend-eng is a skill published in the GitHub repository Recusive/Skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 107 tokens to every session and 1,587 once invoked, about $0.0005 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
ss-lint
Quick automated lint — detects common design system violations in seconds.
spotpatch
A development workflow for React that connects a selected page element to its JSX or TSX source code and gathers context for review.
generic-react-code-reviewer
Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…
review-react
React 19 review (front-app patterns, compiler readiness, Suspense boundaries, hooks discipline) against current official React best practices. USE WHEN: user runs /review-react or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.
review-tanstack-query
TanStack Query review (queryOptions patterns, cache hygiene, mutation flows, devtools) against current official TanStack Query best practices. USE WHEN: user runs /review-tanstack-query or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.
review-tanstack-router
TanStack Router review (file-based routing, route tree generation, typed search params, preload/lazy behavior) against current official TanStack Router best practices. USE WHEN: user runs /review-tanstack-router or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or…