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 skills add dayfinggg/openai-codex-agent-skills --skill react-developmentgit clone --depth 1 https://github.com/dayfinggg/openai-codex-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/dayfinggg/openai-codex-agent-skills/react-development)<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/react-development"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/react-development/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/react-development"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/react-development.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00032 | $0.00231 |
| Opus 5.5 | $0.00013 | $0.00092 |
| Sonnet 5.5 | $0.00006 | $0.00046 |
| Haiku 4.5 | $0.00003 | $0.00023 |
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 today.
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.
What it actually says
Establish the React and framework versions, runtime boundary, changed components, and requested behavior. Preserve the existing component and application contracts.
Read host integration once for the imported rule bundles.
| Task | Read |
|---|---|
| Implement React or Next.js behavior, fetch data, investigate rendering, or optimize a bundle | Performance and implementation rules |
| Design component composition, compound components, state placement, or public props | Composition patterns |
Each procedure retains its individual rules and full compiled guide. Load the specific rules that govern the changed behavior rather than reading both complete guides for every edit.
Use both procedures when a component API redesign also changes rendering or data flow. Use web-design-guidelines separately when the task requires framework-independent accessibility or interface review. Do not introduce optimization machinery without a relevant performance or correctness reason.
What ships with it
60 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.
- references/composition/guide.md 2.5 KB
- references/composition/references/full-guide.md 22 KB
- references/composition/rules/_sections.md 829 B
- references/composition/rules/_template.md 329 B
- references/composition/rules/architecture-avoid-boolean-props.md 2.2 KB
- references/composition/rules/architecture-compound-components.md 2.5 KB
- references/composition/rules/patterns-children-over-render-props.md 1.8 KB
- references/composition/rules/patterns-explicit-variants.md 2.3 KB
- references/composition/rules/react19-no-forwardref.md 953 B
- references/composition/rules/state-context-interface.md 4.9 KB
- references/composition/rules/state-decouple-implementation.md 2.6 KB
- references/composition/rules/state-lift-state.md 3.1 KB
- references/performance/guide.md 6.8 KB
- references/performance/references/full-guide.md 106 KB
- references/performance/rules/_sections.md 1.5 KB
- references/performance/rules/_template.md 631 B
- references/performance/rules/advanced-effect-event-deps.md 1.8 KB
- references/performance/rules/advanced-event-handler-refs.md 1.4 KB
- references/performance/rules/advanced-init-once.md 958 B
- references/performance/rules/advanced-use-latest.md 1.0 KB
- references/performance/rules/async-api-routes.md 1.1 KB
- references/performance/rules/async-cheap-condition-before-await.md 1.2 KB
- references/performance/rules/async-defer-await.md 2.2 KB
- references/performance/rules/async-dependencies.md 1.3 KB
- references/performance/rules/async-parallel.md 654 B
- references/performance/rules/async-suspense-boundaries.md 2.5 KB
- references/performance/rules/bundle-analyzable-paths.md 2.3 KB
- references/performance/rules/bundle-barrel-imports.md 2.7 KB
- references/performance/rules/bundle-conditional.md 949 B
- references/performance/rules/bundle-defer-third-party.md 920 B
- references/performance/rules/bundle-dynamic-imports.md 791 B
- references/performance/rules/bundle-preload.md 1.1 KB
- references/performance/rules/client-event-listeners.md 1.9 KB
- references/performance/rules/client-localstorage-schema.md 1.9 KB
- references/performance/rules/client-passive-event-listeners.md 1.6 KB
- references/performance/rules/client-swr-dedup.md 1.1 KB
- references/performance/rules/js-batch-dom-css.md 3.2 KB
- references/performance/rules/js-cache-function-results.md 1.9 KB
- references/performance/rules/js-cache-property-access.md 532 B
- references/performance/rules/js-cache-storage.md 1.6 KB
- references/performance/rules/js-combine-iterations.md 753 B
- references/performance/rules/js-early-exit.md 1.1 KB
- references/performance/rules/js-flatmap-filter.md 1.4 KB
- references/performance/rules/js-hoist-regexp.md 1.0 KB
- references/performance/rules/js-index-maps.md 837 B
- references/performance/rules/js-length-check-first.md 1.7 KB
- references/performance/rules/js-min-max-loop.md 2.2 KB
- references/performance/rules/js-request-idle-callback.md 2.6 KB
- references/performance/rules/js-set-map-lookups.md 532 B
- references/performance/rules/js-tosorted-immutable.md 1.7 KB
- references/performance/rules/rendering-activity.md 564 B
- references/performance/rules/rendering-animate-svg-wrapper.md 1.2 KB
- references/performance/rules/rendering-conditional-render.md 980 B
- references/performance/rules/rendering-content-visibility.md 815 B
- references/performance/rules/rendering-hoist-jsx.md 1.0 KB
- references/performance/rules/rendering-hydration-no-flicker.md 2.3 KB
- references/performance/rules/rendering-hydration-suppress-warning.md 872 B
- references/performance/rules/rendering-resource-hints.md 2.5 KB
- references/performance/rules/rendering-script-defer-async.md 1.8 KB
- references/performance/rules/rendering-svg-precision.md 588 B
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.
- today First seen · 19 lines · 32 tokens per session scan A a42cf1b1f25f
react-development is a skill published in the GitHub repository dayfinggg/openai-codex-agent-skills (8 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 231 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-30.
Other skills, from other repositories
hook
Create a reusable React hook (useX). Triggers "create hook", "new hook", "custom hook", a useX-style name, or extracting logic out of a component.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
component
Create a UI component. Triggers "create component", "new component", "add component", or naming a component to build (Button, Header, Card).
factory-forms
Form conventions distilled across builds. react-hook-form + Zod via resolver (Mantine or shadcn variant), three Zod schema variants (server strict / client lenient / patch), drawer-CRUD with mode union, field-registry pattern for multi-step forms, declarative conditional visibility with auto-cleanup, debounced…
factory-frontend
Frontend conventions distilled across builds. CRUD shape (DataTable + drawer with mode union), RowActions primitive, format helpers, heading tiers, semantic color tokens, query-key naming, component-library decision criteria (Mantine vs shadcn). Read when scaffolding any UI surface that touches lists, forms, or entity…
factory-forms-builder
Use when building multi-step forms, complex intake flows, drawer-CRUD forms, or anything beyond a one-shot Mantine form. Carries the factory's form conventions — react-hook-form + Zod via resolver, three Zod variants (server strict / client lenient / patch), modular section files from day one, field registry for…