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 rules/sordi-ai/skill-everything/reactgit clone --depth 1 https://github.com/sordi-ai/skill-everythingWhat 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 | $0.00021 | $0.02277 |
| Opus 5 | $0.00010 | $0.01138 |
| Sonnet 5 | $0.00004 | $0.00455 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade A, and why
react 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 yesterday.
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-Skill: React Best Practices
Purpose: Prevents the React-specific mistakes LLMs make repeatedly — wrong state placement, stale closures, unnecessary re-renders, and broken async patterns. Concrete rules with code examples.
Rule classification
- MUST — load-bearing. Violating causes infinite loops, stale data, leaked subscriptions, or invisible UI bugs. Never break.
- SHOULD — default behavior. Deviation needs a documented reason in the code or PR.
- AVOID — usually wrong; documented exception inline where needed.
Where these rules don't strictly apply: test fixtures, Storybook stories, design-system primitives in isolation, and small in-tutorial demo components may legitimately differ. The rules below apply to production application code.
Component Design
-
SHOULD: Co-locate state with the component that owns it. Lift state only when two siblings genuinely share it. Lifting to a grandparent "just in case" causes unnecessary re-renders across the tree.
// Avoid: form state lifted to page-level parent function Page() { const [email, setEmail] = useState(''); return <Form email={email} setEmail={setEmail} />; } // Prefer: state lives in the component that uses it function Form() { const [email, setEmail] = useState(''); return <input value={email} onChange={e => setEmail(e.target.value)} />; } -
SHOULD: Split components at ~100 lines or when a section has its own data concern. One component = one responsibility. Extract
<UserAvatar>,<OrderSummary>rather than one<ProfilePage>that does everything. Exception: pages that are mostly markup with little logic may exceed 100 lines. -
SHOULD: Replace prop drilling beyond two levels with composition or context. Passing
userIdthrough four components to reach a button is a design smell.// Avoid: drilling through intermediaries <Layout userId={userId}><Sidebar userId={userId}><Nav userId={userId} /></Sidebar></Layout> // Prefer: context or render-prop composition <UserContext.Provider value={userId}><Layout /></UserContext.Provider>
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.
- yesterday First seen · 244 lines · 21 tokens per session scan A c22548a6b554
react is a cursor rule published in the GitHub repository sordi-ai/skill-everything (19 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 2,277 once invoked, about $0.0001 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 cursor rules, from other repositories
00-stack
Stack, runtimes, and MCP servers for this repository.
20-testing
How to run tests and MCP smoke checks.
30-security
Secrets, gitleaks, age encryption, telemetry redaction.
obsidian-memory
Markdown vault memory protocol (vkm-kit).
10-style
Style conventions and contribution hygiene.
retention-predictor
Skill — retention-predictor. Predicts retention potential via usage frequency, habit formation mechanics, and churn risk factors.