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/magnus919/agent-skills/reactnpx skills add magnus919/agent-skills --skill reactgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/react)<a href="https://agentmods.dev/skills/magnus919/agent-skills/react"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/react.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.01193 |
| Opus 5 | $0.00057 | $0.00596 |
| Sonnet 5 | $0.00023 | $0.00239 |
| Haiku 4.5 | $0.00011 | $0.00119 |
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 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Application Engineering
Use this skill for the React-specific implementation layer. Preserve the project's existing React version, package manager, build scripts, styling conventions, and routing model unless the user asks for a migration.
Operating loop
- Diagnose before editing. Run
scripts/react-doctor.py --json [PROJECT]and inspectpackage.json, source entry points, Vite config, TypeScript config, routes, and test scripts. The diagnostic is bounded and read-only. - Define the component contract. Identify the page/feature boundary, inputs and outputs, owned state, server state, loading/empty/error/success states, and side effects. Keep reusable components independent of route globals and avoid passing state through unrelated layers.
- Implement with explicit data flow. Prefer local state for local behavior, context only for genuinely cross-cutting concerns, and the existing server state/cache solution for remote data. Keep effects for synchronization with external systems; derive values during render rather than storing duplicates.
- Keep UI resilient. Render a useful loading, empty, error, and success experience. Cancel or ignore stale async work, handle aborts, and avoid setting state after an obsolete request. Preserve stable keys and avoid mutating props or state.
- Build for the browser. Use semantic HTML, keyboard-operable controls, visible focus, responsive layout, and stable accessible names. For detailed accessibility requirements, load web-accessibility.
- Verify in layers. Run the narrowest existing unit/component test, then lint/typecheck, then the production build. For browser-level flows use playwright, not ad hoc browser automation. Report the exact commands and any environment-dependent checks that were skipped.
React-specific rules
- Hooks run unconditionally and in the same order on every render; never call them in branches, loops, event handlers, or nested functions.
- Effects synchronize with external systems. Do not use an effect to calculate a value that can be derived from props/state, or to mirror props into state without a clear user-editing requirement.
- Use functional updates when the next state depends on the previous state. Give list items stable keys from domain identity, not array indexes when the list can reorder, insert, or delete.
- Treat event handlers as user intent and keep them separate from render-time computation. Disable or guard duplicate submissions and expose pending state.
- Keep API response validation and transformation at the integration boundary; components should consume a typed, predictable view model.
- Do not add a state library or router solely because it is popular. First map ownership and use the project's existing choices.
- In Vite, expose only intentionally public variables using the project's
documented prefix (normally
VITE_); never put secrets in client bundles. Read references/vite-diagnostics.md for environment, build, and deployment checks.
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.
- 2d ago First seen · 104 lines · 114 tokens per session scan A e52f11dcfa7c
react is a skill published in the GitHub repository magnus919/agent-skills (67 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 1,193 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.