ai-first-toolkit MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

AI-readiness audit — scores a repo on structure, docs, tests, agent-friendliness
Re-engineering recipes to improve AI-ergonomics of legacy code
Bootstrap skill for greenfield projects with sane defaults
Cross-agent: works in Claude Code and Codex
TypeScript-based tooling

라이브 데모

실제 사용 모습

ai-first-toolkit-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ai-first-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "ai-first-toolkit-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/techwolf-ai/ai-first-toolkit",
        "~/.claude/skills/ai-first-toolkit"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "ai-first-toolkit-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/techwolf-ai/ai-first-toolkit",
          "~/.claude/skills/ai-first-toolkit"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add ai-first-toolkit-skill -- git clone https://github.com/techwolf-ai/ai-first-toolkit ~/.claude/skills/ai-first-toolkit

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: ai-first-toolkit

How to audit a codebase for AI-agent readiness

👤 Tech leads preparing a codebase for heavy AI-assisted work ⏱ ~45 min intermediate

언제 쓸까: Before the team commits to doing a lot of feature work through Claude or Codex.

사전 조건

Skill cloned — git clone https://github.com/techwolf-ai/ai-first-toolkit ~/.claude/skills/ai-first-toolkit

흐름

Run the audit

Audit this repo for AI-agent readiness. Score each dimension and list the top 5 friction points.✓ 복사됨

→ Dimension scores + specific files to fix
Prioritize fixes

Which of those fixes would give the biggest agent-effectiveness lift per hour of work?✓ 복사됨

→ Ranked list with effort/impact
Apply the top fix

Apply fix #1 end-to-end — edit files, update docs, add tests.✓ 복사됨

→ Diff + confirmation

결과: A concrete improvement plan and at least one applied fix making the repo friendlier to AI agents.

함정

Audit turns into a generic 'improve docs' blob — Ask for file:line level findings, not abstract advice

함께 쓰기: filesystem · github

Bootstrap a new AI-friendly project

👤 Founders or ICs starting a new repo ⏱ ~30 min beginner

언제 쓸까: Day zero of a new project, before you pick bad defaults that will haunt you.

흐름

State the project

Bootstrap a new TypeScript API project using ai-first-toolkit defaults. Purpose: internal billing API.✓ 복사됨

→ Proposed folder structure, tsconfig, scripts, README skeleton
Scaffold the files

Create the files. Include AGENTS.md and CLAUDE.md with the relevant codebase notes.✓ 복사됨

→ Repo files materialized
First commit

Initialize git and make the first commit with a clean message.✓ 복사됨

→ Clean initial repo

결과: A new repo that's friendly to both humans and AI agents from commit 0.

함정

Scaffolding imports dependencies you don't want — Ask Claude to list dependencies before installing — accept each one

함께 쓰기: github · filesystem

Re-engineer a messy module for AI readability

👤 Engineers paying down tech debt one module at a time ⏱ ~60 min advanced

언제 쓸까: You've isolated a module that Claude keeps getting wrong — usually a sign its structure isn't agent-legible.

흐름

Diagnose the module

Look at src/billing/. What about this code makes it hard for an agent to edit safely?✓ 복사됨

→ Specific red flags: indirection, hidden state, long functions
Plan the refactor

Propose a 3-step refactor that improves agent-legibility without changing public API.✓ 복사됨

→ Stepwise plan with diff sketches
Execute step 1

Apply step 1. Keep tests green.✓ 복사됨

→ PR-sized diff

결과: A module that Claude can actually reason about on the next iteration.

함정

Over-refactor and break behaviors you didn't mean to — Insist on public API stability and run tests after each step

함께 쓰기: filesystem · github

조합

다른 MCP와 조합해 10배 효율

ai-first-toolkit-skill + filesystem

Audit scans the repo; filesystem is needed to actually read it

Walk the repo and score AI-readiness; report findings file-by-file.✓ 복사됨

ai-first-toolkit-skill + github

Open a PR with the proposed AGENTS.md / CLAUDE.md additions

Apply the audit's top 3 fixes and open a PR titled 'AI-first improvements'.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출
ai-readiness-audit	repo root	Pre-investment in AI-heavy workflows
ai-first-bootstrap	project spec (lang, purpose, stack)	Greenfield projects
re-engineer-module	module path + goals	When a module resists agent edits

비용 및 제한

운영 비용

API 쿼터: none beyond your LLM provider
호출당 토큰: 5–20k for an audit of a medium repo
금액: free, open source
팁: Scope audits to a subtree rather than the whole monorepo

보안

권한, 시크릿, 파급범위

자격 증명 저장: none

데이터 외부 송신: none beyond what filesystem/github tools do

문제 해결

자주 발생하는 오류와 해결

Audit is too abstract

Re-prompt with a concrete dimension: 'evaluate just the test layout' or 'just the module boundaries'.

Bootstrap picks wrong language

Always state language+runtime+build tool in the first prompt.

대안

ai-first-toolkit 다른 것과 비교

대안	언제 쓰나	단점/장점
init (built-in)	You just need a CLAUDE.md and don't care about the rest	Narrower scope
antivibe-skill	You want the opposite lens — critique of AI-shaped sludge	Diagnostic, not prescriptive

ai-first-toolkit