react-development

A set of instructions for building and maintaining React interfaces, which are web interfaces made from reusable components. It covers components, data, forms, navigation, accessibility, testing, and rendering behavior.

In plain words
What is it for?
Use it when creating, reviewing, debugging, or maintaining React components, hooks, forms, routes, data fetching, or framework integrations.
Why use it?
It helps prevent common interface problems such as broken loading and error states, inaccessible controls, hydration errors, and interaction regressions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/code-saurabh/openskills/react-development
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill react-development
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.03555
Opus 5 $0.00026 $0.01777
Sonnet 5 $0.00010 $0.00711
Haiku 4.5 $0.00005 $0.00356

Measured yesterday against content hash 182030123802, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-development 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.

react-development/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Development

Act as the React engineer responsible for an interface that remains correct through loading, failure, navigation, concurrent rendering, assistive technology, and future product changes. Build around user tasks and data ownership, not component count or hook cleverness.

Execution Workflow

  1. Inspect the app architecture. Identify React version, framework/rendering model, router, styling system, component library, state/query libraries, test stack, API conventions, and existing accessibility patterns.
  2. Model the flow and state. Define the user task, server/client state, transitions, permissions, loading/empty/error/success states, URL state, and mutation recovery before coding.
  3. Compose the interface. Create focused components around meaningful boundaries. Keep fetch and mutation ownership close to the feature boundary; pass explicit props and callbacks.
  4. Implement accessible behavior. Use semantic HTML, native controls where possible, keyboard interactions, focus management, and clear feedback.
  5. Verify runtime behavior. Test primary and failure paths, inspect responsive layouts, and check for hydration, render, and interaction regressions.

Step 0: Ground the Feature in a User Flow

Before creating components, establish:

  1. User job: What does a person need to see, decide, or complete?
  2. Route and rendering model: Which route owns this feature and is it server-rendered, client-rendered, streamed, or static?
  3. State ownership: What is server state, URL state, local draft state, shared UI state, and derived state?
  4. Permissions and outcomes: Who can perform the action, what succeeds, and what can fail or be retried?
  5. Acceptance proof: Which keyboard flow, viewport, data state, and test demonstrate completion?

Inspect the route, nearby components, styling/tokens, data/query layer, router, existing primitives, and tests before adding a new pattern. Preserve an intentional design system; do not create a competing button, dialog, fetch wrapper, or state store for one feature.

Read the full file on GitHub · 273 lines

Changes

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.

  1. yesterday First seen · 273 lines · 51 tokens per session scan A 182030123802

Subscribe to this mod's changes

react-development is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 3,555 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 2026-08-31.