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 coco-research/coco --skill vercel-react-best-practicesgit clone --depth 1 https://github.com/coco-research/cocoWrote 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/coco-research/coco/vercel-react-best-practices)<a href="https://agentmods.dev/skills/coco-research/coco/vercel-react-best-practices"><img src="https://agentmods.dev/badge/skills/coco-research/coco/vercel-react-best-practices/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/coco-research/coco/vercel-react-best-practices"><img src="https://agentmods.dev/badge/skills/coco-research/coco/vercel-react-best-practices.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 | $0.00035 | $0.00223 |
| Opus 5.5 | $0.00014 | $0.00089 |
| Sonnet 5.5 | $0.00007 | $0.00045 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
vercel-react-best-practices 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 22d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
58 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.
- AGENTS.md 80 KB
- rules/advanced-event-handler-refs.md 1.4 KB
- rules/advanced-init-once.md 958 B
- rules/advanced-use-latest.md 1.0 KB
- rules/async-api-routes.md 1.1 KB
- rules/async-defer-await.md 2.0 KB
- rules/async-dependencies.md 1.3 KB
- rules/async-parallel.md 654 B
- rules/async-suspense-boundaries.md 2.5 KB
- rules/bundle-barrel-imports.md 2.3 KB
- rules/bundle-conditional.md 949 B
- rules/bundle-defer-third-party.md 920 B
- rules/bundle-dynamic-imports.md 791 B
- rules/bundle-preload.md 1.1 KB
- rules/client-event-listeners.md 1.9 KB
- rules/client-localstorage-schema.md 1.9 KB
- rules/client-passive-event-listeners.md 1.6 KB
- rules/client-swr-dedup.md 1.1 KB
- rules/js-batch-dom-css.md 3.2 KB
- rules/js-cache-function-results.md 1.9 KB
- rules/js-cache-property-access.md 532 B
- rules/js-cache-storage.md 1.6 KB
- rules/js-combine-iterations.md 753 B
- rules/js-early-exit.md 1.1 KB
- rules/js-hoist-regexp.md 1.0 KB
- rules/js-index-maps.md 837 B
- rules/js-length-check-first.md 1.7 KB
- rules/js-min-max-loop.md 2.2 KB
- rules/js-set-map-lookups.md 532 B
- rules/js-tosorted-immutable.md 1.7 KB
- rules/rendering-activity.md 564 B
- rules/rendering-animate-svg-wrapper.md 1.2 KB
- rules/rendering-conditional-render.md 980 B
- rules/rendering-content-visibility.md 815 B
- rules/rendering-hoist-jsx.md 1.0 KB
- rules/rendering-hydration-no-flicker.md 2.3 KB
- rules/rendering-hydration-suppress-warning.md 872 B
- rules/rendering-svg-precision.md 588 B
- rules/rendering-usetransition-loading.md 2.0 KB
- rules/rerender-defer-reads.md 973 B
- rules/rerender-dependencies.md 824 B
- rules/rerender-derived-state-no-effect.md 1.2 KB
- rules/rerender-derived-state.md 728 B
- rules/rerender-functional-setstate.md 2.9 KB
- rules/rerender-lazy-state-init.md 2.0 KB
- rules/rerender-memo-with-default-value.md 1.1 KB
- rules/rerender-memo.md 1.1 KB
- rules/rerender-move-effect-to-event.md 1.2 KB
- rules/rerender-simple-expression-in-memo.md 1018 B
- rules/rerender-transitions.md 1.0 KB
- rules/rerender-use-ref-transient-values.md 1.7 KB
- rules/server-after-nonblocking.md 2.0 KB
- rules/server-auth-actions.md 2.6 KB
- rules/server-cache-lru.md 1.3 KB
- rules/server-cache-react.md 2.2 KB
- rules/server-dedup-props.md 2.0 KB
- rules/server-parallel-fetching.md 1.5 KB
- rules/server-serialization.md 996 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.
- 22d ago Changed · -114 lines · -17 tokens per session 59f1ee83b12d
- 1mo ago Changed · -15 tokens per session fbda1daf6ca7
- 1mo ago First seen · 138 lines · 67 tokens per session scan A 27eaf8620f6d
vercel-react-best-practices is a skill published in the GitHub repository coco-research/coco (795 stars, last pushed today), with no licence file. It adds 35 tokens to every session and 223 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 2026-09-03.
Other skills, from other repositories
frontend-ux-engineer
Use for frontend features, Next.js/React/Vue/Svelte UI, accessibility, responsive layout, design polish, state handling, forms, visual QA, or product workflow improvements.
nextjs-fullstack
Use for Next.js App Router, React Server Components, server actions, API routes, auth, database integration, caching, deployment, or full-stack product features.
react
Apply when writing React components. Hook discipline, state placement, performance, async cleanup, and list keys.
cinematic-website-prime-directive
One-line-prompt → cinematic, gorgeous, functional, well-tested, deployed website. Pre-hydrated SPA + full PWA kit + JSON-LD rich snippets + third-party integrations. React 19+Vite default (Angular optional). 100 concrete improvements grouped into 10 categories that EVERY single-prompt site build must satisfy before…
site-generation
End-to-end AI website generation pipeline. Claude Opus 4.8 emits Bolt-style envelopes (multi-file, plan-first) that customize Vite+React+Tailwind templates from pre-researched business data. Pre-research via APIs, media acquisition, brand extraction, visual inspection via GPT Image 2 vision, R2 upload (per-file…
frontend-conventions
Locks in opinionated frontend code patterns for Next.js 16 + TanStack Query v5 + FSD projects. ALWAYS invoke when writing data-fetching code (NEVER useEffect+fetch — always TanStack Query), creating forms (always react-hook-form + zod), introducing client state (Zustand for client-global only — NEVER for server data…