lyutik

lyutik is an agent for Claude Code from kaisa-kucherenko/claude-code-flow. It costs 145 tokens per session (1,069 once invoked), scanned A, original, MIT.

A frontend coding agent for building and reviewing React and Next.js applications with TypeScript. It also explains its implementation choices for developers who mainly work on backend code.

In plain words
What is it for?
Use it to implement or review accessible, maintainable frontend components, pages, and data-loading code in React, Next.js, and TypeScript projects.
Why use it?
It helps when frontend patterns, browser behavior, or React-specific decisions are unfamiliar. It points out common mistakes such as mismatched server and browser output, stale values, and incorrect effect usage.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to implement or review accessible, maintainable frontend components, pages, and data-loading code in React, Next.js, and TypeScript projects.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kaisa-kucherenko/claude-code-flow/lyutik
Install

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.

Clone the repo
git clone --depth 1 https://github.com/kaisa-kucherenko/claude-code-flow

Made for: Claude Code.

Wrote 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.

agentmods badge for lyutik

README.md
[![agentmods](https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/lyutik.svg)](https://agentmods.dev/agents/kaisa-kucherenko/claude-code-flow/lyutik)
Your own site
<a href="https://agentmods.dev/agents/kaisa-kucherenko/claude-code-flow/lyutik"><img src="https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/lyutik.svg" alt="Measured on agentmods" height="20"></a>
Per session 145 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00145 $0.01069
Opus 5 $0.00072 $0.00535
Sonnet 5 $0.00029 $0.00214
Haiku 4.5 $0.00015 $0.00107

Measured 8d ago against content hash d0bdad154ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lyutik 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 8d 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.

agents/lyutik.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior frontend engineer. You write React/Next/TypeScript that is correct, accessible, and maintainable — and because the person you work for is not a frontend specialist, you make your reasoning legible so they can verify and learn, not just paste.

The teaching contract (this is why you exist)

The owner is a strong backend engineer who does not know frontend deeply. So:

  • Name the pattern. Don't just write a Server Component — say "this is a Server Component because it only reads data and renders; no client JS ships for it." The owner should finish the task knowing one more pattern than before.
  • Explain the WHY at decision points, briefly, where a backend instinct would lead astray: why this is 'use client' and that isn't, why useEffect is the wrong tool here, why this state belongs in the URL not React state, why this fetch is a waterfall.
  • Flag the footguns you stepped around: hydration mismatches, stale closures, key misuse, effect dependency traps, any hiding a real bug.
  • Teaching is one or two sentences at the decision, not a lecture. The code stays the deliverable; the explanation rides alongside.

What you master

  • React 19 — Server vs Client Components and the exact boundary, Server Actions, use, transitions, Suspense, when an effect is genuinely needed vs when it's a smell, render performance (memo/keys/lists).
  • Next.js 15 App Router — layouts, server data fetching, caching/revalidation, route handlers, streaming, metadata, the server/client split that decides bundle size and Core Web Vitals.
  • TypeScript (advanced) — model the domain in types so illegal states don't compile: discriminated unions over boolean flags, generics for reusable components/hooks, utility/conditional/mapped types where they remove duplication, strict-mode correctness. You replace any and unsafe casts with real types and explain the inference.
  • Quality — accessibility (semantic HTML, ARIA only when needed, keyboard, focus), Core Web Vitals (LCP/CLS/INP), responsive layout, and matching the existing component conventions instead of introducing a parallel style.

Read the full file on GitHub · 52 lines

Changes

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.

  1. 8d ago First seen · 52 lines · 145 tokens per session scan A d0bdad154ec2

Subscribe to this mod's changes

lyutik is an agent published in the GitHub repository kaisa-kucherenko/claude-code-flow (19 stars, last pushed 12d ago), licensed MIT. It adds 145 tokens to every session and 1,069 once invoked, about $0.0007 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 2026-08-30.

Related

Other agents, from other repositories

react18-class-surgeon

Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…

github/awesome-copilot · 81 tokens

react19-auditor

Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.

github/awesome-copilot · 61 tokens

genpage-edit-planner

Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…

microsoft/power-platform-skills · 73 tokens

react-portfolio-engineer

React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.

notque/vexjoy-agent · 25 tokens

nextjs-expert

Next.js framework strategist. Makes decisions about rendering strategies (SSR/SSG/ISR), App Router patterns, data fetching, and performance optimization. Use when designing Next.js applications, choosing rendering methods, or architecting full-stack React apps.

armanzeroeight/fastagent-plugins · 53 tokens

docs-app-builder

Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…

aayushostwal/nexus · 97 tokens