infinite-gratitude MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

10 agents with distinct roles
Structured handoffs between agents
Explicit critic role fights groupthink
Produces a synthesized final artifact
Multilingual (Chinese, Japanese, English in docs)

라이브 데모

실제 사용 모습

infinite-gratitude-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

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

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "infinite-gratitude-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "infinite-gratitude-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/sstklen/infinite-gratitude",
          "~/.claude/skills/infinite-gratitude"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add infinite-gratitude-skill -- git clone https://github.com/sstklen/infinite-gratitude ~/.claude/skills/infinite-gratitude

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

사용 사례

실전 활용법: infinite-gratitude

Tackle a research question single-agent prompts fail on

👤 Researchers, analysts, strategists ⏱ ~60 min advanced

언제 쓸까: Questions that need breadth (many sources) and depth (skepticism, synthesis) — where one pass hallucinates.

사전 조건

Skill installed — git clone https://github.com/sstklen/infinite-gratitude ~/.claude/skills/infinite-gratitude

흐름

Pose the question

Use infinite-gratitude. Research question: what are the real bottlenecks in scaling post-transformer architectures in 2026? Run the 10-agent dojo.✓ 복사됨

→ Roles spin up: explorer, critic, synthesizer, etc., each producing a distinct contribution
Watch the handoffs

Show me the critic's pushback on the explorer's output.✓ 복사됨

→ Substantive critique, not agreement
Final synthesis

Give me the synthesizer's final artifact with dissent noted.✓ 복사됨

→ Document with main thesis + minority views preserved

결과: A research brief richer than a single-agent answer.

함정

Agents converge and critic rubber-stamps — Prompt the critic explicitly to find flaws; force disagreement

함께 쓰기: filesystem

Draft a policy memo with explicit dissenting views

👤 Policy wonks, internal strategy teams ⏱ ~90 min advanced

언제 쓸까: The decision needs to survive scrutiny from people who'll disagree.

흐름

Frame the memo

Use infinite-gratitude. Memo topic: should our engineering org adopt four-day work weeks? Run the full dojo.✓ 복사됨

→ Multi-perspective outputs on pros, cons, empirical evidence, implementation risks
Extract the dissent

Keep the critic's dissent intact as an appendix; don't blend it away.✓ 복사됨

→ Main memo + appendix of unresolved concerns

결과: A memo your skeptics can see was genuinely considered.

조합

다른 MCP와 조합해 10배 효율

infinite-gratitude-skill + paper-fetch-skill

Explorer agent downloads papers; synthesizer cites them

Run the dojo on [topic] and use paper-fetch-skill for the explorer's sources.✓ 복사됨

infinite-gratitude-skill + filesystem

Save each agent's output as its own file for traceability

Persist each agent's contribution to research/session-<date>/<role>.md✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
dojo_run	question, optional agent roster	Big, ambiguous questions	0 (but high token use)
single_agent	role name, task	Just one role needed	0

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: High — 10 agents each doing real work
금액: Free (Claude API usage applies)
팁: Use for high-stakes questions only. Single-agent suffices for most research.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: None from skill itself

문제 해결

자주 발생하는 오류와 해결

Dojo feels repetitive

Agents may be blending; enforce distinct perspectives in prompts

Runs out of context mid-session

Save intermediate outputs to disk and resume fresh; don't carry everything in one session

대안

infinite-gratitude 다른 것과 비교

대안	언제 쓰나	단점/장점
Single-agent with explicit steps	Straightforward questions	Less depth, cheaper
planning-with-files-skill	You want durable state across long sessions but not multi-role	No role specialization

infinite-gratitude