Auto Idea
autopus-ai/autopus-adk
아이디어 브레인스토밍 — 멀티 프로바이더 토론과 ICE 평가로 아이디어를 정리합니다. An agent skill from autopus-ai/autopus-adk.
프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다
MITAuto-check passed
Install Auto Setup
$ npx skills add autopus-ai/autopus-adk --skill auto-setup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autopus-ai/autopus-adk auto-setup --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.omp/skills/auto-setup .claude/skills/auto-setup && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "auto-setup" agent skill from https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setup into .claude/skills/auto-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-setup", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setupType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add autopus-ai/autopus-adk --skill auto-setup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autopus-ai/autopus-adk auto-setup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.omp/skills/auto-setup .agents/skills/auto-setup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "auto-setup" agent skill from https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setup into .agents/skills/auto-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-setup", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autopus-ai/autopus-adk --skill auto-setup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autopus-ai/autopus-adk auto-setup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.omp/skills/auto-setup .cursor/skills/auto-setup && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "auto-setup" agent skill from https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setup into .cursor/skills/auto-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-setup", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/autopus-ai/autopus-adk.git --path .omp/skills/auto-setup--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add autopus-ai/autopus-adk --skill auto-setup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autopus-ai/autopus-adk auto-setup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.omp/skills/auto-setup .gemini/skills/auto-setup && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "auto-setup" agent skill from https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setup into .gemini/skills/auto-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-setup", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install autopus-ai/autopus-adk auto-setupInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add autopus-ai/autopus-adk --skill auto-setup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk.git skills-src && mkdir -p .github/skills && cp -r skills-src/.omp/skills/auto-setup .github/skills/auto-setup && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "auto-setup" agent skill from https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setup into .github/skills/auto-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-setup", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autopus-ai/autopus-adk --skill auto-setup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autopus-ai/autopus-adk auto-setup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.omp/skills/auto-setup .opencode/skills/auto-setup && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "auto-setup" agent skill from https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setup into .opencode/skills/auto-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-setup", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
auto-setup- GitHub stars
- 111
- Token cost
- ~1.5k tokens
- SKILL.md length
- 726 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다
- Works in 3 steps: 항상 표시 가능: /auto review, /auto idea → SPEC이 없으면: /auto plan "기능 설명" → draft SPEC이 있으면: /auto go {SPEC-ID} 또는…
- SKILL.md covers OMP Invocation, 설명, Workspace Folder Boundary and 사용법, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Auto Setup is an agent skill from autopus-ai/autopus-adk. 프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: omp
The repository describes itself as: Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking… The licence is MIT.
Example prompts
- “/auto-setup”
Requirements
- Docker
- Compatibility (from SKILL.md): omp
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 항상 표시 가능: /auto review, /auto idea
- SPEC이 없으면: /auto plan "기능 설명"
- draft SPEC이 있으면: /auto go {SPEC-ID} 또는 auto spec review {SPEC-ID}
What it can do on your machine
Read from SKILL.md and the folder at commit 3f15677. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
omp
From compatibility in the SKILL.md frontmatter.
Context cost
Auto Setup loads about 1.5k tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 726 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from autopus-ai/autopus-adk at commit 3f15677, republished under its MIT licence (© autopus-ai). 726 words, ~1,525 tokens.
Download SKILL.mdSave it as
.claude/skills/auto-setup/SKILL.md (or your agent's skills folder).- name
- auto-setup
- description
- 프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다
- compatibility
- omp
auto-setup — 프로젝트 컨텍스트 생성 스킬
OMP Invocation
/auto setup .../auto-setup ...- Load detail skill
auto-setupfor either entrypoint.
프로젝트: autopus-adk | 모드: full
설명
프로젝트 구조와 기술 스택을 분석해 세션 간 지속되는 컨텍스트 문서를 생성하거나 갱신합니다.
이 스킬은 첫 세션 온보딩, 오래된 프로젝트 재진입, /auto plan//auto sync 전 컨텍스트 복구에 사용합니다.
Workspace Folder Boundary
ADK는 workspace folder profile의 소유자가 아니라 workspace 또는 repo checkout 안에 설치되는 harness/execution layer입니다. auto setup은 루트 역할과 추적 정책을 문서화하지만, canonical Knowledge Hub의 folder identity, promotion, admission 정책을 ADK generated surface로 대체하지 않습니다.
Generated/runtime/harness surfaces are excluded from canonical Knowledge Hub indexing unless they are explicitly human-managed project/spec documents:
- Excluded:
.autopus/runtime/**,.autopus/qa/{runs,cache,gui,feedback,evidence,releases}/**raw artifacts,.autopus/context/signatures.md,.autopus/*-manifest.json,.autopus/plugins/**,.autopus/orchestra/**,.autopus/brainstorms/**,.autopus/design/{imports,verify}/**,.autopus/canary/**,.codex/**,.claude/**,.gemini/**,.opencode/**,.agents/{skills,plugins,commands}/**,.agents/hooks.json,.symphony/artifacts/**,config.toml - Indexable local docs:
.autopus/project/**,.autopus/specs/**,.autopus/vault/**,README.md,docs/** - Candidate/projection only:
.autopus/inbox/**requires promotion; sanitized.autopus/learnings/pipeline.jsonlrows remain ADK Decision/Quality Index projection evidence.
사용법
/auto setup
/auto setup --autoCodex 기본 실행 모델
- Codex에서는
setup도taskbatch 기반 subagent-first 로 진행합니다. - Step 1의 전체 코드베이스 분석은 반드시
explorer서브에이전트로 먼저 수행합니다. - 메인 세션은 결과를 검토한 뒤
ARCHITECTURE.md와.autopus/project/*산출물을 최종 정리하고 저장합니다. - 현재 Codex 런타임 정책이 암묵적
taskbatch 호출을 제한하면, 하네스 기본값과 제약을 명시적으로 설명한 뒤 사용자에게 서브에이전트 진행 여부 또는--solo성격의 단일 세션 진행을 확인받습니다.
전체 라우팅 규칙은 /auto setup 라우터를 우선합니다.
실행 순서
[REQUIRED] Step 1: 코드베이스 분석
IMPORTANT: 이 단계는 반드시 explorer 서브에이전트를 먼저 호출해야 합니다. 분석 없이 Step 2로 건너뛰면 안 됩니다.
explorer 에이전트가 최소한 아래 정보를 반환하게 합니다.
- 디렉터리 구조와 패키지 역할
- 루트 저장소 역할(product repo / monorepo root / meta workspace)과 nested git repo 경계
- 기술 스택(언어, 프레임워크, 빌드 도구)
- 엔트리포인트와 주요 공개 API
- 아키텍처 패턴과 도메인 경계
- 사용자 접점이 있는 라우트, 명령, 화면
- generated surface / runtime artifact 경로와 source-of-truth repo
- ADK가 harness layer이며 folder profile owner가 아니라는 경계
- canonical Knowledge Hub에서 제외되는 generated/runtime/harness surface와 indexable/candidate/projection-only 경로
- QA/Journey Pack 대상 리포,
auto qa init --project-dir <repo>실행 명령, 루트.autopus/qa/**가 project-owned인지 runtime/generated인지
POST-STEP: explorer 결과를 받으면 Step 2로 진행합니다. 탐색 요약 없이 완료 안내를 출력하지 않습니다.
[REQUIRED] Step 2: ARCHITECTURE.md 생성 또는 갱신
Explorer 분석을 바탕으로 루트 ARCHITECTURE.md를 작성합니다.
포함 항목:
- 핵심 도메인과 레이어
- 의존성 흐름 및 경계
- 진입점과 주요 데이터 흐름
- 관찰된 규칙 위반 또는 위험 지점
POST-STEP:
ARCHITECTURE.md저장 후 Step 3으로 진행합니다.
[REQUIRED] Step 3: .autopus/project/ 핵심 문서 생성 또는 갱신
다음 4개 파일을 explorer 결과 기준으로 작성합니다.
product.md— 프로젝트 목적, 핵심 기능, 주요 유스케이스, 모드structure.md— 디렉터리 구조, 패키지 역할, 엔트리포인트, 주요 파일 분포tech.md— 언어, 프레임워크, 빌드/테스트 도구, 아키텍처 패턴workspace.md— 루트 저장소 역할, nested repo 경계, generated/runtime 경로, 추적/커밋 정책, source-of-truth 위치, QA/Journey Pack 대상 리포와auto qa init --project-dir <repo>명령
규칙:
- 추측보다 실제 코드베이스 증거를 우선합니다.
- monorepo면 workspace/module 경계를 드러냅니다.
- meta workspace면 keep 대상과 generated/runtime drop 대상을 명시합니다.
- meta workspace면 root
.autopus/qa/**를 제품 Journey Pack 위치로 쓰지 말고, 대상 리포별--project-dir명령을 문서에 남깁니다. - 기존 파일이 있어도 현재 상태를 반영해 갱신합니다.
structure.md는 package family와 경계만 요약합니다. 개별 파일을 전수 나열하지 말고 18,000 bytes 이하를 목표로 하며, doctor warning 경계인 20,000 bytes를 넘기지 않습니다.
POST-STEP:
.autopus/project/4개 파일 저장 후 Step 4로 진행합니다.
Show full SKILL.md (224 more words)Show less
[REQUIRED] Step 4: scenarios.md 생성 또는 갱신
.autopus/project/scenarios.md에 사용자 관점 E2E 시나리오를 정리합니다.
프로젝트 유형별로 다음을 추출합니다.
- CLI: 주요 명령, 플래그, 정상/실패 경로
- API: 메서드, 경로, 인증/사전조건, 기대 응답
- Frontend: 핵심 페이지, 사용자 동작, 검증 포인트
- Library: 공개 API 진입점과 대표 사용 시나리오
각 시나리오는 최소한 아래를 포함합니다.
- Command/Action
- Precondition
- Expect
- Verify
- Status
POST-STEP:
scenarios.md저장 후 Step 5로 진행합니다.
[REQUIRED] Step 5: canary.md 생성 또는 갱신
.autopus/project/canary.md에 빌드/엔드포인트/브라우저 건강 검진 대상을 정의합니다.
우선 탐지 대상:
Dockerfile,docker-compose.ymlrailway.json,vercel.json,fly.toml,render.yamlk8s/,helm/.github/workflows/- 소스 코드의 health/status endpoint
- 프론트엔드 라우트와 대표 브라우저 타깃
최소 산출물:
- build health check
- endpoint health check 또는 해당 없음
- browser health check 또는 해당 없음
- detection source 요약
POST-STEP:
canary.md저장 후 Pre-Completion Verification으로 진행합니다.
[REQUIRED] Pre-Completion Verification
완료 메시지 전에 아래 항목이 모두 충족됐는지 확인합니다.
- Step 1: explorer 서브에이전트 호출 완료
- Step 2:
ARCHITECTURE.md저장 완료 - Step 3:
.autopus/project/product.md,structure.md,tech.md,workspace.md저장 완료 - Step 4:
.autopus/project/scenarios.md저장 완료 - Step 5:
.autopus/project/canary.md저장 완료
하나라도 비어 있으면 완료 메시지를 출력하지 말고 해당 단계로 돌아갑니다.
Completion Message
Project context documents have been generated/updated.
- ARCHITECTURE.md
- .autopus/project/product.md
- .autopus/project/structure.md
- .autopus/project/tech.md
- .autopus/project/workspace.md
- .autopus/project/scenarios.md
- .autopus/project/canary.md
Context will be loaded automatically on the next session.First Win Guidance
완료 후 현재 상태에 맞는 다음 액션을 최대 3개까지 추천합니다.
우선순위:
- 항상 표시 가능:
/auto review,/auto idea - SPEC이 없으면:
/auto plan "기능 설명" - draft SPEC이 있으면:
/auto go {SPEC-ID}또는auto spec review {SPEC-ID}
출력 형식:
🐙 바로 해볼 수 있는 것 ──────────────
1. {command} — {one-line value}출력
ARCHITECTURE.md.autopus/project/product.md.autopus/project/structure.md.autopus/project/tech.md.autopus/project/workspace.md.autopus/project/scenarios.md.autopus/project/canary.md
© autopus-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .omp/skills/auto-setup of autopus-ai/autopus-adk.
Open the folder on GitHubat commit 3f15677
More from autopus-ai/autopus-adk
All 11 skills in this repoAuto QA
autopus-ai/autopus-adk
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence
Auto Sync
autopus-ai/autopus-adk
문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다. An agent skill from autopus-ai/autopus-adk.
Ax Annotation
autopus-ai/autopus-adk
@AX code annotation workflow skill for agent-driven tag application
Browser Automation
autopus-ai/autopus-adk
터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증. An agent skill from autopus-ai/autopus-adk.
Codebase Design
autopus-ai/autopus-adk
작은 인터페이스 뒤에 많은 동작을 숨기는 deep module을 설계하기 위한 공용 어휘(module, interface, seam, adapter, depth)와 원칙
Questions about Auto Setup
What does Auto Setup do?
프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다. Auto Setup is an agent skill from autopus-ai/autopus-adk.
How do I install Auto Setup in Claude Code?
Run `npx skills add autopus-ai/autopus-adk --skill auto-setup -a claude-code`. Or copy the skill folder (.omp/skills/auto-setup in autopus-ai/autopus-adk) into .claude/skills/auto-setup in your project. Claude Code loads it when a task matches its description.
How do I install Auto Setup in Codex?
Run `npx skills add autopus-ai/autopus-adk --skill auto-setup -a codex`. Or copy the skill folder (.omp/skills/auto-setup in autopus-ai/autopus-adk) into .agents/skills/auto-setup in your project. Codex loads it when a task matches its description.
Can I use Auto Setup in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autopus-ai/autopus-adk --skill auto-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-setup, .gemini/skills/auto-setup, .github/skills/auto-setup and .opencode/skills/auto-setup in your project.
What does Auto Setup need to run?
SKILL.md names no scripts, command-line tools or credentials: Auto Setup is instructions for the agent only. Our summary lists: Docker. Compatibility (from SKILL.md): omp.
Does Auto Setup access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Auto Setup safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Auto Setup use?
Auto Setup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Auto Setup use?
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Who maintains Auto Setup?
autopus-ai (a GitHub organization) maintains it in autopus-ai/autopus-adk, which has 111 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 4, 2026.
Source: autopus-ai/autopus-adk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.