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 smicolon/ai-kit --skill react-perf-rulesgit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/smicolon/ai-kit/react-perf-rules)<a href="https://agentmods.dev/skills/smicolon/ai-kit/react-perf-rules"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/react-perf-rules/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/smicolon/ai-kit/react-perf-rules"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/react-perf-rules.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 | $0.00040 | $0.00403 |
| Opus 5.5 | $0.00016 | $0.00161 |
| Sonnet 5.5 | $0.00008 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
react-perf-rules 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 1mo 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.
What it actually says
React & Next.js Performance Review Rules
Prioritized review rules to audit branches for performance regressions.
Severity Classification
P0 (Critical — Must Fix Before Merge)
- Sequential Waterfalls: Unnecessary chained
awaitstatements in server components or route handlers that could be parallelized withPromise.all(). - Accidental De-opt of Server Components: Adding
'use client'to layout roots or high-level containers instead of leaf nodes. - Unbounded Client-Side Lists: Rendering dynamic lists with 100+ items without virtualization or pagination.
- Missing Memoization on Expensive Render Trees: Passing new inline functions/objects as props to expensive or memoized child subtrees.
P1 (High Impact — Strong Recommendation)
- Massive Barrel Imports: Importing icons or utilities from index barrel files that bypass bundler tree-shaking.
- Synchronous Heavy Operations in Route Handlers: Missing
after()for non-critical side effects (audit logging, telemetry) in Next.js 15. - Uncached Cacheable Fetches in Next.js 15: Relying on legacy Next.js 14 caching assumptions without explicit
revalidateorcache: 'force-cache'. - Derived State Synced via
useEffect: Storing computed values inuseStateand setting them inuseEffectinstead of calculating inline during render.
P2 (Medium / Polish)
- Missing
next/imagedimensions / priority: Hero images missingprioritycausing LCP delay. - Unoptimized Third-Party Scripts: Analytics or chat widgets loaded eagerly rather than
lazyOnload.
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.
- 1mo ago First seen · 28 lines · 40 tokens per session scan A a212a4e85bd4
react-perf-rules is a skill published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 403 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.
seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking,"…
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.
review-ticket
Review a ticket or PR through focused specialist lenses: scope, architecture, security, tests, AC coverage, and PR metadata.
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence, or to make a feature reel (see reel mode…