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/code-saurabh/openskills/react-developmentnpx skills add CODE-SAURABH/OpenSkills --skill react-developmentgit clone --depth 1 https://github.com/CODE-SAURABH/OpenSkillsWhat 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 | $0.00051 | $0.03555 |
| Opus 5 | $0.00026 | $0.01777 |
| Sonnet 5 | $0.00010 | $0.00711 |
| Haiku 4.5 | $0.00005 | $0.00356 |
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.
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
- 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.
- 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.
- Compose the interface. Create focused components around meaningful boundaries. Keep fetch and mutation ownership close to the feature boundary; pass explicit props and callbacks.
- Implement accessible behavior. Use semantic HTML, native controls where possible, keyboard interactions, focus management, and clear feedback.
- 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:
- User job: What does a person need to see, decide, or complete?
- Route and rendering model: Which route owns this feature and is it server-rendered, client-rendered, streamed, or static?
- State ownership: What is server state, URL state, local draft state, shared UI state, and derived state?
- Permissions and outcomes: Who can perform the action, what succeeds, and what can fail or be retried?
- 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.
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 · 273 lines · 51 tokens per session scan A 182030123802
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.
Other skills, from other repositories
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
aria
Designs the data model, API contracts, and structural foundation of the system.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").
ecommerce-landing-page
Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.
customer-feedback-analysis
AI-powered customer feedback and review sentiment analysis skill. Extracts pain points, feature requests, and improvement priorities from customer reviews across e-commerce platforms.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.