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/dean0x/devflow/reactnpx skills add dean0x/devflow --skill reactgit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00065 | $0.01392 |
| Opus 5 | $0.00032 | $0.00696 |
| Sonnet 5 | $0.00013 | $0.00278 |
| Haiku 4.5 | $0.00006 | $0.00139 |
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Patterns
Reference for React-specific patterns with citations. Sources in references/sources.md.
Iron Law
COMPOSITION OVER PROPS [2][4][12]
Use children and compound components, not prop drilling. If a component has >5 props, it's doing too much. Split it. If you're passing data through 3+ levels, use context or composition. Props are for configuration, not data plumbing. "Before You memo(), try solving it with composition." — Dan Abramov [4]
When This Skill Activates
- Working with React codebases (.tsx, .jsx) — components, hooks, contexts, performance
Component Structure [1][2]
Functional component order: hooks → derived state → handlers → return. [1]
Compound components share structure through children, not props: [2][4]
function Card({ children }: { children: React.ReactNode }) {
return <div className="card">{children}</div>;
}
Card.Header = ({ children }: { children: React.ReactNode }) =>
<div className="card-header">{children}</div>;
Context for shared state across distant components — eliminates prop drilling: [1][2]
const AuthContext = createContext<AuthContextValue | null>(null);
export function useAuth() {
const ctx = useContext(AuthContext);
if (!ctx) throw new Error('useAuth must be used within AuthProvider');
return ctx;
}
Hooks [3][16][24]
Hooks must be called at the top level — never inside conditions, loops, or nested functions. [16][24] Effects synchronize with external systems; they are not lifecycle methods. [3] Every effect that subscribes must return a cleanup function. Deps must be complete — never omit to suppress warnings. [3]
See references/hooks.md for rules of hooks, custom hooks, useReducer, and effect anti-patterns.
Performance [3][4][5][17]
The React Compiler (2024) handles many memoizations automatically [17]. For manual optimization, follow this priority: [4]
- Composition first — "before you memo(), try passing children down" [4]
- Extract primitives for
useEffectdeps — avoid object/array literals [3] useMemofor expensive computations;useCallbackfor stable handlers [3]React.memoonly when parent has stable, memoized callbacks [4]- Virtualize long lists (react-window) [5]; lazy-load heavy components [5]
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 144 lines · 65 tokens per session scan A 936491bc0c1e
react is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 1,392 once invoked, about $0.0003 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
data-engineering
Skill "data-engineering" from fengshao1227/ccg-workflow, covering 数据工程域 · data engineering, 域概览, 数据管道编排, 框架对比 and airflow 核心模式.
verify-change
变更校验关卡。分析代码变更,检测文档同步状态,评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。.
verify-security
安全校验关卡。自动扫描代码安全漏洞,检测危险模式,确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
gen-docs
文档生成器。自动分析模块结构,生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。.
verify-module
模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。.