skills-benchmarks is a test suite that measures how the design of skill documentation affects Claude Code's adherence to recommended coding patterns. It is used to compare documentation approaches across LangChain-related tasks and other agent workflows. Its catalogue entries represent skills, hooks, instructions, and a plugin used in the benchmark project.
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 langchain-ai/skills-benchmarks --skill react_componentsgit clone --depth 1 https://github.com/langchain-ai/skills-benchmarksWrote 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/langchain-ai/skills-benchmarks/react_components)<a href="https://agentmods.dev/skills/langchain-ai/skills-benchmarks/react_components"><img src="https://agentmods.dev/badge/skills/langchain-ai/skills-benchmarks/react_components/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/langchain-ai/skills-benchmarks/react_components"><img src="https://agentmods.dev/badge/skills/langchain-ai/skills-benchmarks/react_components.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Prompt Injection · line 12 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 | $0.00012 | $0.00444 |
| Opus 5.5 | $0.00005 | $0.00178 |
| Sonnet 5.5 | $0.00002 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
react-components 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 Component Patterns
Build maintainable React components using modern patterns.
Functional Components with Hooks
Always prefer functional components over class components:
import { useState, useEffect, useCallback } from 'react';
interface UserProps {
userId: string;
onUpdate?: (user: User) => void;
}
export function UserProfile({ userId, onUpdate }: UserProps) {
const [user, setUser] = useState<User | null>(null);
const [loading, setLoading] = useState(true);
useEffect(() => {
fetchUser(userId).then(setUser).finally(() => setLoading(false));
}, [userId]);
const handleSave = useCallback(async (data: UserData) => {
const updated = await updateUser(userId, data);
setUser(updated);
onUpdate?.(updated);
}, [userId, onUpdate]);
if (loading) return <Skeleton />;
if (!user) return <NotFound />;
return <UserForm user={user} onSave={handleSave} />;
}
Custom Hooks
Extract reusable logic into custom hooks:
function useAsync<T>(asyncFn: () => Promise<T>, deps: any[]) {
const [state, setState] = useState<AsyncState<T>>({
loading: true,
error: null,
data: null,
});
useEffect(() => {
setState(s => ({ ...s, loading: true }));
asyncFn()
.then(data => setState({ loading: false, error: null, data }))
.catch(error => setState({ loading: false, error, data: null }));
}, deps);
return state;
}
Component Composition
Use composition over prop drilling:
<Card>
<Card.Header>Title</Card.Header>
<Card.Body>{content}</Card.Body>
<Card.Footer>
<Button>Action</Button>
</Card.Footer>
</Card>
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 · 79 lines · 12 tokens per session scan A c3d12886f029
react-components is a skill published in the GitHub repository langchain-ai/skills-benchmarks (118 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 444 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
client-setup
Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.
adapter-express
Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.
trpc-router
Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.
custom-features
Implement a Table v9 plugin when built-ins and typed meta are insufficient. Covers FeatureMaps, runtime lifecycle hooks, prototypes, and a complete checked example.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
port-sacred-terminal-ui-to-typescript-cli
Take a React Window.tsx (or any sacred component) and produce a terminal CLI screen written in TypeScript that uses Simulacrum — the sacred CLI framework in scripts/cli/lib/.