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 yonatangross/orchestkit --skill react-server-components-frameworkgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/react-server-components-framework)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/react-server-components-framework"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/react-server-components-framework/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/yonatangross/orchestkit/react-server-components-framework"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/react-server-components-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 37 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- high Agent Snooping · line 164 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- medium MCP Rug Pull · line 37 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 164 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00048 | $0.02646 |
| Opus 5.5 | $0.00019 | $0.01058 |
| Sonnet 5.5 | $0.00010 | $0.00529 |
| Haiku 4.5 | $0.00005 | $0.00265 |
Grade A, and why
react-server-components-framework scanned grade A with 1 finding 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 20d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
await fetch(url, { cache: 'force-cache' }) How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Server Components Framework
Overview
React Server Components (RSC) enable server-first rendering with client-side interactivity. This skill covers Next.js 16.2 LTS App Router patterns, Server Components, Server Actions, and streaming.
Next.js 16.2.6 / React 19.2.6 (security release, May 2026) — Turbopack is the default bundler (no
--turboflag needed), Server Fast Refresh is on by default, and the newcacheComponentsconfig flag replaces the legacyexperimental_pprescape hatch. For AI-agent debugging Next.js ships Next DevTools MCP — wirenpx -y next-devtools-mcp@latestinto.mcp.json(it connects via the dev server's/_next/mcpendpoint) to inspect render trees and cache boundaries mid-session.
When to use this skill:
- Building Next.js 16+ applications with the App Router
- Designing component boundaries (Server vs Client Components)
- Implementing data fetching with caching and revalidation
- Creating mutations with Server Actions
- Optimizing performance with streaming and Suspense
Quick Reference
Server vs Client Components
| Feature | Server Component | Client Component |
|---|---|---|
| Directive | None (default) | 'use client' |
| Async/await | Yes | No |
| Hooks | No | Yes |
| Browser APIs | No | Yes |
| Database access | Yes | No |
| Client JS bundle | Zero | Ships to client |
Key Rule: Server Components can render Client Components, but Client Components cannot directly import Server Components (use children prop instead).
Data Fetching Quick Reference
Next.js 16 Cache Components (Recommended):
import { cacheLife, cacheTag } from 'next/cache'
// Default — shared across all users (public CDN-cached)
async function CachedProducts() {
'use cache'
cacheLife('hours')
cacheTag('products')
return await db.product.findMany()
}
// Remote variant (16.2+) — always served from the edge/CDN, never rendered
// inline on the origin. Best for static product listings, marketing content.
async function MarketingHero() {
'use cache: remote'
cacheLife('days')
return <Hero />
}
// Private variant (16.2+) — cached per-user session. Never shared across
// users. Use for personalized dashboards with expensive computation.
async function UserDashboard({ userId }: { userId: string }) {
'use cache: private'
cacheLife('minutes')
cacheTag(`user:${userId}`)
return await loadDashboard(userId)
}
// Invalidate cache — v16 requires a cacheLife profile as the 2nd arg
import { revalidateTag } from 'next/cache'
revalidateTag('products', 'max') // or updateTag('products') for read-your-writes
What ships with it
16 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.
- examples/blog-app-example.tsx 12 KB
- references/capability-details.md 2.9 KB
- references/ork-delta.md 3.8 KB
- references/tanstack-router-patterns.md 9.9 KB
- rules/_sections.md 812 B
- rules/_template.md 339 B
- rules/rsc-cache-safety.md 2.8 KB
- rules/rsc-client-boundaries.md 2.6 KB
- rules/rsc-component-types.md 2.4 KB
- rules/rsc-hydration.md 2.6 KB
- rules/rsc-serialization.md 2.9 KB
- scripts/client-component-template.tsx 2.0 KB
- scripts/create-server-component.md 2.4 KB
- scripts/server-action-template.ts 6.1 KB runs code
- scripts/server-component-template.tsx 1.9 KB
- test-cases.json 5.0 KB
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.
- 20d ago Changed · -1 lines 32bdb84463ea
- 27d ago Changed 7bcfdd47f10b
- 28d ago Changed · -5 lines 1af58f0413c6
- 29d ago Changed · -1 lines ffb82bfdb779
- 1mo ago Changed df46565e5bed
- 1mo ago Changed f90034bafcab
- 1mo ago First seen · 268 lines · 48 tokens per session scan A 227ca1d9901c
react-server-components-framework is a skill published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,646 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
decocms-ui
Build or style React UI with the decocms product design system (@decocms/ui). Use when creating a new screen, page, or component that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers screen layout (width…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
ai-agentic-workflows
Use this skill when the user says 'agentic workflow', 'agent loop', 'ReAct', 'plan and execute', 'planner executor', 'reflection loop', 'evaluator-optimizer', 'prompt chaining', 'LangGraph workflow'. Designs the control flow around an LLM: which workflow pattern to pick (chain, router, parallel, orchestrator-workers…
cali
Use when working in the Cali repository or when you need to run, extend, or debug the Cali CLI for mobile React Native and Expo workflows. Covers Cali commands (qa, review, perf-review, dev), the shared cali-context.json contract, local mode selection, required local CLIs, provider setup, and CI integration patterns.
Agent Workflow Builder
Build multi-agent AI workflows with orchestration, tool use, and state management.
pn-threejs-core
Guides Three.js scenes, cameras, lighting, asset loading, animation, physics, and performance. Use when working on Three.js; covers scene structure, R3F/Drei patterns, WebGPU migration (r171+), TSL shaders, and compute shaders.