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/recca0120/code-quest/react-compilernpx skills add recca0120/code-quest --skill react-compilergit clone --depth 1 https://github.com/recca0120/code-questWhat 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 | $0.00107 | $0.02429 |
| Opus 5 | $0.00053 | $0.01215 |
| Sonnet 5 | $0.00021 | $0.00486 |
| Haiku 4.5 | $0.00011 | $0.00243 |
Grade A, and why
react-compiler scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Compiler 1.0 — 實際行為與邊界
This project uses React Compiler. 不亂加 useMemo / useCallback 才對,但也不是全部自動。
本 skill 的結論以
babel-plugin-react-compiler實際編譯輸出為準,不依賴推論。有疑問時用下面的 probe script 跑看。
What Compiler DOES auto-memoize(不要再加 useMemo)
以下所有情境 Compiler 都會插入 cache slots(if ($[0] !== dep) 形式)自動 memo。手動 useMemo 是純冗餘:
1. Component 內部的 JSX / callback / 物件字面值
function Counter() {
const [count, setCount] = useState(0);
const increment = () => setCount((n) => n + 1); // auto-memo
const meta = { count, isZero: count === 0 }; // auto-memo on [count]
return <Button onClick={increment}>{count}</Button>; // JSX auto-memo
}
2. Hook 回傳值的 spread
export function useSession() {
const state = useContext(StateCtx);
const actions = useContext(ActionsCtx);
if (!state || !actions) throw new Error('...');
return { ...state, ...actions }; // auto-memo on [state, actions]
}
3. Hook 內的 filter / map / reduce / sort
export function useVisibleItems() {
const { items, filter } = useContext(ListContext);
return items.filter((item) => item.status === filter); // auto-memo on [items, filter]
}
4. 合併預設值
export function useConfig(overrides?: Partial<Config>) {
return { ...DEFAULT_CONFIG, ...overrides }; // auto-memo on [overrides]
}
5. Provider value inline object
return <Ctx.Provider value={{ socket }}>{children}</Ctx.Provider>; // auto-memo on [socket]
// 跟以下寫法編譯後完全一樣:
const value = useMemo(() => ({ socket }), [socket]);
return <Ctx.Provider value={value}>{children}</Ctx.Provider>;
What Compiler does NOT do(這 3 件必須手動)
這是架構限制,Compiler 沒辦法替你處理:
邊界 1:Component boundary memoization
Compiler 不會自動把 child component 包成 React.memo。Parent render → child 被呼叫,即使 child 自己 context 沒變。
手動處理時機:
- 渲染成本高的 leaf component(Markdown / syntax highlight / 大型表格 row)
- 深 provider tree 的邊界(memo 一次 short-circuit 整片 subtree)
- 吃 props 但 props 多半穩定的 container
不值得 memo:
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.
- 2d ago First seen · 243 lines · 107 tokens per session scan A 59d36fa8a75a
react-compiler is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 2,429 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…