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 performancegit 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/performance)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/performance"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/performance/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/performance"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium MCP Rug Pull · line 162 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 | $0.00064 | $0.03345 |
| Opus 5.5 | $0.00026 | $0.01338 |
| Sonnet 5.5 | $0.00013 | $0.00669 |
| Haiku 4.5 | $0.00006 | $0.00334 |
Grade A, and why
performance 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 16d 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.
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance
Comprehensive performance optimization patterns for frontend, backend, and LLM inference.
Quick Reference
| Category | Rules | Impact | When to Use |
|---|---|---|---|
| Core Web Vitals | 4 | CRITICAL | LCP, INP, CLS optimization with 2026 thresholds |
| Render Optimization | 3 | HIGH | React Compiler, memoization, virtualization |
| Lazy Loading | 3 | HIGH | Code splitting, route splitting, preloading |
| Image Optimization | 2 | HIGH | AVIF/WebP formats, responsive images |
| Profiling & Backend | 3 | MEDIUM | React DevTools, py-spy, bundle analysis |
| LLM Inference | 3 | MEDIUM | vLLM, quantization, speculative decoding |
| Caching | 2 | HIGH | Redis cache-aside, prompt caching, HTTP cache headers |
| Query & Data Fetching | 2 | HIGH | TanStack Query prefetching, optimistic updates, rollback |
| Sustainability | 1 | MEDIUM | Page weight budgets, lazy loading, optimized formats, dark mode |
Total: 23 rules across 9 categories
Core Web Vitals
Google's Core Web Vitals with 2026 stricter thresholds.
| Rule | File | Key Pattern |
|---|---|---|
| LCP Optimization | rules/cwv-lcp.md |
Preload hero, SSR, fetchpriority="high" |
| INP Optimization | rules/cwv-inp.md |
scheduler.yield, useTransition, requestIdleCallback |
| INP Advanced | rules/cwv-inp-advanced.md |
Layout thrashing, third-party scripts, rAF patterns |
| CLS Prevention | rules/cwv-cls.md |
Explicit dimensions, aspect-ratio, font-display |
2026 Thresholds
| Metric | Current Good | 2026 Good |
|---|---|---|
| LCP | <= 2.5s | <= 2.0s |
| INP | <= 200ms | <= 150ms |
| CLS | <= 0.1 | <= 0.08 |
Render Optimization
React render performance patterns for React 19+.
| Rule | File | Key Pattern |
|---|---|---|
| React Compiler | rules/render-compiler.md |
Auto-memoization, "Memo" badge verification |
| Manual Memoization | rules/render-memo.md |
useMemo/useCallback escape hatches, state colocation |
| Virtualization | rules/render-virtual.md |
TanStack Virtual for 100+ item lists |
What ships with it
43 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/orchestkit-performance-wins.md 20 KB
- metadata.json 497 B
- references/cc-prompt-cache-guide.md 2.1 KB
- references/database-optimization.md 3.9 KB
- references/ork-delta.md 2.0 KB
- rules/_sections.md 3.0 KB
- rules/_template.md 339 B
- rules/caching-http.md 2.8 KB
- rules/caching-redis.md 2.9 KB
- rules/cwv-cls.md 2.2 KB
- rules/cwv-inp-advanced.md 4.2 KB
- rules/cwv-inp.md 2.7 KB
- rules/cwv-lcp.md 2.4 KB
- rules/images-formats.md 2.4 KB
- rules/images-responsive.md 2.6 KB
- rules/inference-quantization.md 2.8 KB
- rules/inference-speculative.md 3.1 KB
- rules/inference-vllm.md 2.8 KB
- rules/loading-lazy.md 2.4 KB
- rules/loading-preload.md 2.9 KB
- rules/loading-splitting.md 2.5 KB
- rules/profiling-backend.md 2.6 KB
- rules/profiling-bundle.md 2.6 KB
- rules/profiling-react.md 2.7 KB
- rules/query-optimistic.md 3.5 KB
- rules/query-prefetching.md 2.9 KB
- rules/render-compiler.md 2.0 KB
- rules/render-memo.md 2.5 KB
- rules/render-virtual.md 3.2 KB
- rules/sustainability-ux.md 3.7 KB
- scripts/api-optimization.ts 3.0 KB runs code
- scripts/caching-patterns.ts 2.2 KB runs code
- scripts/database-optimization.ts 2.4 KB runs code
- scripts/frontend-optimization.tsx 3.8 KB
- scripts/image-component.tsx 4.7 KB
- scripts/lazy-component.tsx 1.9 KB
- scripts/optimized-context.tsx 6.0 KB
- scripts/performance-metrics.ts 2.9 KB runs code
- scripts/performance-monitoring.ts 18 KB runs code
- scripts/quantization-config.py 16 KB runs code
- scripts/virtualized-list.tsx 3.9 KB
- scripts/vllm-server.py 9.0 KB runs code
- test-cases.json 11 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.
- 16d ago Changed · -1 lines 7bb22f8fd51c
- 24d ago Changed · -5 lines f174f06f54d0
- 25d ago Changed · -1 lines a97f9d575533
- 1mo ago Changed bf5116741ff0
- 1mo ago Changed 176d0bcae2dd
- 1mo ago First seen · 334 lines · 64 tokens per session scan A 36778cf44ea8
performance is a skill published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 3,345 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
microprofile-server
Architecture and coding rules for long-running Java MicroProfile / Jakarta EE server applications — BCE layering, business components (BC), JAX-RS resources, CDI, JSON-P, testing (unit/integration/system), and Maven project structure. Use when creating, generating, scaffolding, writing, or reviewing code, resources…
tool-design
Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise). Use when writing a new tool for an agent, reviewing or fixing an existing tool definition, deciding how to split capabilities…
api-crud-generator
A code generator that creates standard Next.js API routes and an administration page from Prisma models. Prisma is a tool that describes and accesses an application’s database.
pn-backend-architecture
Scalable system design, database schemas, API contracts, microservices patterns. Use when designing APIs, DBs, or infrastructure before or during backend implementation.
pn-backend-scaffolding
Scaffolds new API routes, modules, or services in Node (Express, Fastify, Hono) or similar. Use when adding a new route/module/service; covers project layout, env/secrets pattern, error-handling stub, and stack-specific conventions. Reference pn-node-api and pn-backend-philosophy for design rules.
pn-node-api
Guides Node/API design, DB access patterns, and env/secrets. Use when designing or implementing Node/API code; covers API design, error handling, config, and DB patterns.