freainer

A setup command for configuring Claude Code with recommended MCP servers, language tools, and notification hooks. MCP servers give the coding agent extra tools, while a language server helps it understand code structure.

In plain words
What is it for?
Use it to install Context7 for current library documentation, Playwright for browser automation, Draw.io for diagrams, and a language server suited to the type of project you develop.
Why use it?
It reduces the manual work of installing and checking common development tools for a new Claude Code setup.

Command

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.

agentmods
npx agentmods add commands/imgompanda/fireauto/freainer
Clone the repo
git clone --depth 1 https://github.com/imgompanda/fireauto
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,276 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00028 $0.03276
Opus 5 $0.00014 $0.01638
Sonnet 5 $0.00006 $0.00655
Haiku 4.5 $0.00003 $0.00328

Measured yesterday against content hash c76c2f66d0f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

freainer scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

유저의 `~/.claude/settings.json`을 읽고, `env` 필드에 아래를 추가하세요:
plugin/commands/freainer.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FreAiner 원클릭 세팅

Claude Code를 처음 쓰는 사람도 커맨드 하나로 프로급 환경을 만들 수 있어요.


Step 1: 추천 MCP 자동 설치

아래 3개 MCP를 자동으로 설치하세요. 전부 무료이고 API 키가 필요 없어요.

1-1. Context7 (최신 문서 참조)

라이브러리/프레임워크의 최신 공식 문서를 실시간으로 가져와요. AI가 오래된 정보 대신 정확한 최신 문서를 참고해요.

claude mcp add context7 -- npx -y @upstash/context7-mcp

설치 후 확인:

claude mcp list

context7이 목록에 있으면 성공이에요.

1-2. Playwright (브라우저 자동화)

AI가 브라우저를 직접 조작해요. 웹 테스트, 스크린샷, 페이지 조작이 가능해요.

claude mcp add playwright -- npx -y @playwright/mcp@latest

1-3. Draw.io (다이어그램 생성)

AI가 아키텍처도, 플로우차트, ERD를 직접 그려줘요. 브라우저에서 바로 편집 가능해요.

claude mcp add drawio -- npx -y @drawio/mcp

3개 모두 설치한 후 claude mcp list로 확인하세요. context7, playwright, drawio가 모두 보이면 완료예요.


Step 2: LSP 설치 (코드 탐색 강화)

LSP를 켜면 AI가 코드를 텍스트 검색 대신 구조를 이해하면서 탐색해요.

유저에게 물어보세요:

어떤 개발을 주로 하세요?

  1. 웹 개발 (React, Next.js, Vue 등)
  2. 백엔드 개발 (Node.js, Python, Go 등)
  3. iOS 개발 (Swift, SwiftUI)
  4. 안드로이드 개발 (Kotlin, Java)
  5. 시스템 개발 (Rust, C, C++)
  6. 게임 개발 (Unity C#, Unreal C++)
  7. 자동 감지 (프로젝트 파일 보고 판단)

선택에 따라 아래 Language Server를 설치하세요:

카테고리 설치할 Language Server
웹 개발 TypeScript (typescript-language-server), CSS (vscode-css-languageserver-bin)
백엔드 (Node) TypeScript (typescript-language-server)
백엔드 (Python) Python (pyright)
백엔드 (Go) Go (gopls)
iOS Swift (sourcekit-lsp) — Xcode와 함께 설치됨
안드로이드 Kotlin (kotlin-language-server)
시스템 (Rust) Rust (rust-analyzer)
시스템 (C/C++) C/C++ (clangd)
게임 (Unity) C# (omnisharp)
자동 감지 프로젝트의 package.json, requirements.txt, go.mod 등을 확인하고 적절한 것을 설치

웹 개발 예시 (가장 흔한 케이스):

npm install -g typescript typescript-language-server

LSP 환경변수 설정:

유저의 ~/.claude/settings.json을 읽고, env 필드에 아래를 추가하세요:

{
  "env": {
    "ENABLE_LSP_TOOL": "1"
  }
}

이미 env 필드가 있으면 기존 값을 유지하고 ENABLE_LSP_TOOL만 추가하세요.

LSP 플러그인 활성화:

선택한 카테고리에 맞는 LSP 플러그인을 enabledPlugins에 추가하세요:

Read the full file on GitHub · 333 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. yesterday First seen · 333 lines · 28 tokens per session scan B c76c2f66d0f0

Subscribe to this mod's changes

freainer is a command published in the GitHub repository imgompanda/fireauto (140 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 3,276 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.