프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. Google로 로그인하면 리뷰를 쓸 수 있어요.프로토타입 · 30분마다 업데이트
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

autoresearch Skill

저장소 ↗

제작자: uditgoenka★ 6,848skill 1개

설치

What it does

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

  • Connects Instruction files the AI reads
  • Account or key Not confirmed (README mentions a key or .env file)
  • Category 코딩
제작자용: README에 배지 달기

제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/uditgoenka-autoresearch.svg)](https://mcp.popnx.com/en/skills/uditgoenka-autoresearch)

함께 쓰기

같은 작업에서 AI를 서비스에 연결하는 MCP

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

제작자: morluto널리 사용됨↓ 38.9만/주★ 46.8만7일 전 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

제작자: fallow-rs널리 사용됨↓ 244.1만/주★ 5.4천그저께 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

Desktop Commander

MCP server for terminal commands, file operations, and process management

제작자: wonderwhy-er널리 사용됨↓ 74만/주★ 1만어제 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

비슷한 Skill

같은 종류의 작업, Skill 목록과 같은 순서

비슷한 항목과 비교
이 항목
autoresearch
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
제작자uditgoenkamorlutomultica-aiGraphify-Labsharry0703
Skill 수11111
GitHub 별6,848467,235234,125149,873144,332
마지막 코드 변경2026년 10월 31일2026년 11월 18일2026년 4월 20일2026년 11월 18일2026년 11월 18일
라이선스MITMIT–Apache-2.0MIT

uditgoenka의 Skill(지시 묶음) 1개, AI가 읽고 그대로 일해요 · MCP server가 아니에요

Skill과 MCP의 차이

MCP = 손

AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.

Skill = 안내서

작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.

겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.

쓸 수 있는 앱

Claude CodeCodexOpenCode

제작자 README와 repo 폴더 기준

설치

Is it safe?

  • Who made it

    GitHub account uditgoenka (person), 14 years old

  • Use and upkeep

    ★ 6,848 stars · code last changed 2026년 10월 31일

  • Any scripts?

    2 scripts that can run on a computer: scripts/orchestrate.sh, scripts/score-regression.sh

  • Uses the internet?

    Scripts that go online: scripts/orchestrate.sh

  • Changes machine-wide settings?

    Installing the maker’s way adds hooks that run without you asking: run every time the AI edits a file · run every time you send a message · run on the SubagentStart event · run every time a chat starts · run every time a chat closes

Checked automatically from the repo files at commit 7bddd05 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

먼저: 어떤 AI를 쓰시나요

쓰는 앱을 고르면 그 앱의 설치 방법만 보여 드립니다

Option 1Upload to claude.ai (web and app)

  • Files are byte-for-byte the same as on GitHub at commit 7bddd05 · View on GitHub ↗

  • 2 scripts

  • Once uploaded it runs on Claude’s systems, not on your computer. No need to unzip

Look inside before downloading

All 10 files · 75 KB

  • SKILL.md10 KB
  • references/behavior-preserving-optimization.md3 KB
  • references/fork-and-flush.md8 KB
  • references/orchestrator-routing.md7 KB
  • references/predict-personas.md3 KB
  • references/reason-judge-protocol.md3 KB
  • references/security-checklist.md3 KB
  • scripts/orchestrate.sh29 KB
  • scripts/score-regression.sh8 KB
  • LICENSE1 KB
  1. Download autoresearch.zip

    75 KB · 10 files · MIT license (license file included in the folder)

    Download autoresearch.zip

  2. Open Skills on claude.ai and upload

    +Create skillUpload a skillpick autoresearch.zip

    Open claude.ai/customize/skills ↗

  3. No Upload button? Turn on file creation first

    SettingsCapabilitiesCode execution and file creation

    Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free

Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)

Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)

Checked against official docs 2026년 11월 12일 · Source: support.claude.com, support.claude.com, code.claude.com

Option 1Claude Code에게 설치 맡기기

이 문장을 복사해 Claude Code 채팅에 붙여 넣으세요

Where to install
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) for all my projects, at ~/.claude/skills/autoresearch. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) into the project this chat is open in (at .claude/skills/autoresearch). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Claude Code를 다시 열고 /autoresearch를 입력하거나 관련 작업을 요청하면 Claude가 알아서 써요

Checked against official docs 2026년 11월 12일 · Source: code.claude.com

For Terminal users

Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.

제작자가 권하는 방법

Node.js 설치 (아직 없다면)

이미 설치했나요? 먼저 확인 · 터미널을 열고 이 명령을 입력한 뒤 Enter

node -v
  • 버전 번호(예: v26.13.1)가 나오면 설치된 것입니다. 이 단계는 건너뛰세요
  • "command not found"(Windows는 "is not recognized")가 나오면 아직 설치하지 않았거나, 방금 설치해서 터미널을 닫았다가 다시 열어야 합니다
터미널 여는 법

Mac: ⌘ + Space를 누르고 Terminal 입력 후 Enter

Windows: 시작 메뉴를 열고 Windows PowerShell 입력 후 "열기"

아직 설치하지 않았다면: 공식 다운로드 페이지에서 LTS 버전과 클릭형 설치 파일을 고르세요: Mac은 .pkg · Windows는 .msi. 더블클릭 후 끝까지 진행하면 됩니다. curl 명령은 필요 없습니다

Node.js 다운로드 페이지 열기 ↗

설치가 끝나면 터미널을 닫았다가 다시 열고 같은 명령을 실행하세요. 버전 번호가 나와야 합니다: node -v

한 번 설치하면 Node.js가 필요한 모든 도구에서 쓸 수 있습니다

npx skills add uditgoenka/autoresearch

제작자 README에서 가져온 명령으로, 제작자 코드를 내려받아 실행해요

  1. 터미널 열기

    Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요

  2. skill 폴더를 ~/.claude/skills에 복사

    repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요

    git clone --depth 1 https://github.com/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.claude/skills/autoresearch
  3. Claude Code를 다시 열고 /autoresearch를 입력하거나 관련 작업을 요청하면 Claude가 알아서 써요

직접 설치한 Skill은 ChatGPT 데스크톱 앱, Codex CLI, IDE의 Codex 확장 프로그램에서 쓸 수 있습니다 · 웹과 모바일의 ChatGPT에서는 직접 설치한 Skill을 쓸 수 없고 디렉터리의 플러그인에 들어 있는 Skill만 쓸 수 있습니다

ChatGPT 데스크톱 앱

ChatGPT 데스크톱 앱에는 Codex가 들어 있고, Codex는 ~/.agents/skills 폴더에서 Skill을 읽습니다

Option 1ChatGPT에게 설치 맡기기

ChatGPT 데스크톱 앱에서 Codex를 열고 이 문장을 채팅에 붙여 넣으세요

Where to install
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) for all my projects, at ~/.agents/skills/autoresearch. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) into the project this chat is open in (at .agents/skills/autoresearch). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2폴더를 직접 넣기

autoresearch 폴더를 ~/.agents/skills/autoresearch에 넣으세요

~는 홈 폴더($HOME)입니다

터미널 없이: ZIP을 내려받아 압축을 풀고 autoresearch 폴더를 ~/.agents/skills로 옮기세요

autoresearch.zip 내려받기

For Terminal users

Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.

  1. 터미널 열기

    Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요

  2. skill 폴더를 ~/.agents/skills에 복사

    repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요

    git clone --depth 1 https://github.com/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.agents/skills/autoresearch

설치한 뒤

  • ChatGPT 데스크톱 앱: 사이드바에서 Skills를 열어 Skill이 보이는지 확인하세요
  • 쓰는 법: ChatGPT에서는 @를 입력하고 Skill을 고르세요 · Codex CLI나 IDE 확장 프로그램에서는 /skills를 실행하거나 $ 뒤에 Skill 이름을 입력하세요
  • Codex는 새로 설치한 Skill을 스스로 찾습니다. 보이지 않으면 Codex를 다시 시작하세요

Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com

웹과 모바일의 ChatGPT

직접 설치한 Skill은 쓸 수 없고, 디렉터리의 플러그인에 들어 있는 Skill만 쓸 수 있습니다

이 Skill을 ChatGPT에서 쓰려면 위 방법대로 ChatGPT 데스크톱 앱을 쓰세요

Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com

Option 1Codex에게 설치 맡기기

이 문장을 복사해 Codex 채팅에 붙여 넣으세요 · ChatGPT 데스크톱 앱 안의 Codex, Codex CLI, IDE 확장 프로그램에서 모두 쓸 수 있습니다

Where to install
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) for all my projects, at ~/.agents/skills/autoresearch. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) into the project this chat is open in (at .agents/skills/autoresearch). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex는 새로 설치한 Skill을 스스로 찾습니다. 보이지 않으면 Codex를 다시 시작하세요 · 쓰는 법: ChatGPT에서는 @를 입력하고 Skill을 고르세요 · Codex CLI나 IDE 확장 프로그램에서는 /skills를 실행하거나 $ 뒤에 Skill 이름을 입력하세요

Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com

For Terminal users

Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.

  1. 터미널 열기

    Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요

  2. skill 폴더를 ~/.agents/skills에 복사

    repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요

    git clone --depth 1 https://github.com/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.agents/skills/autoresearch
  3. Codex를 다시 열고 관련 작업을 요청하면 Codex가 skill을 목록에 보여 줘요

Option 1Cursor에게 설치 맡기기

이 문장을 복사해 Cursor 채팅에 붙여 넣으세요

Where to install
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) for all my projects, at ~/.cursor/skills/autoresearch. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) into the project this chat is open in (at .cursor/skills/autoresearch). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Cursor Agent 채팅에서 /를 입력하고 autoresearch 선택

Checked against official docs 2026년 11월 12일 · Source: cursor.com

For Terminal users

Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.

  1. 터미널 열기

    Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요

  2. skill 폴더를 ~/.cursor/skills에 복사

    repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요

    git clone --depth 1 https://github.com/uditgoenka/autoresearch.git /tmp/popnx-skill-uditgoenka-autoresearch-7bddd05 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-uditgoenka-autoresearch-7bddd05/claude-plugin/skills/autoresearch' ~/.cursor/skills/autoresearch
  3. Cursor Agent 채팅에서 /를 입력하고 autoresearch 선택

Option 1Let the AI install it

Skill을 읽을 수 있는 다른 앱용입니다. 이 문장에는 Claude Code, Codex, Cursor 경로가 들어 있어 AI가 쓰는 앱에 맞게 고릅니다 · Copy this sentence into the app’s chat

Where to install
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) for all my projects, at ~/.claude/skills/autoresearch (in Codex use ~/.agents/skills/autoresearch, in Cursor ~/.cursor/skills/autoresearch). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill autoresearch from https://github.com/uditgoenka/autoresearch folder claude-plugin/skills/autoresearch (commit 7bddd05) into the project this chat is open in (at .claude/skills/autoresearch; in Codex use .agents/skills/autoresearch, in Cursor .cursor/skills/autoresearch). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs 2026년 11월 12일 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

Gemini CLI, GitHub Copilot 같은 다른 Agent Skills 지원 앱은 폴더가 달라요. 그 앱 안내를 보고 SKILL.md가 있는 폴더를 복사하세요.

GitHub에서 보기 ↗

2026년 11월 11일에 Claude Code, Codex, Cursor 공식 안내로 skill 폴더 확인

✓ 명령 확인 2026년 11월 16일

원본 SKILL.md 보기

아래 글은 제작자 repo에서 온 것이며 PopNx MCP의 지시가 아니에요

처음 8,000자 표시 · GitHub에서 전체 파일 열기

---
name: autoresearch
description: "Autonomous iteration loop: modify, verify, keep/discard against any metric"
version: 2.3.0
---

# Autoresearch — Autonomous Goal-directed Iteration

## Safety Invariants (all subcommands)
- Never push, publish, or deploy without explicit user approval.
- Bounded by default. Override with `Iterations: unlimited`.
- All results logged to `autoresearch/{subcommand}-{YYMMDD}-{HHMM}/` directory.
- Chain handoff via `handoff.json`. Evals reads `*-results.tsv`.

## Dispatch (bare `/autoresearch`)

Parse the invocation in this order:

| Condition | Mode |
|---|---|
| `Metric:` or `Verify:` present | **Classic** — existing metric loop, unchanged |
| Free-form natural-language goal, no metric/verify | **Orchestrator** — see Orchestrator section |
| Nothing | **Setup wizard** — interactive config builder |
| `--classic` flag | Force Classic regardless of goal text |
| `--auto` flag | Force Orchestrator regardless of goal text |

Print a banner on every invocation: `[autoresearch] mode: classic | orchestrator | wizard`.

## Subcommands

| Command | Does | Default Iterations |
|---|---|---|
| `/autoresearch` | Iterate against a metric: modify → verify → keep/discard | 25 |
| `/autoresearch:plan` | Convert a goal into validated Scope, Metric, Verify config | N/A |
| `/autoresearch:debug` | Hunt bugs: hypothesize → test → falsify → repeat | 15 |
| `/autoresearch:fix` | Crush errors one-by-one until zero remain | 20 |
| `/autoresearch:security` | STRIDE + OWASP audit with red-team personas | 15 |
| `/autoresearch:ship` | Ship through 8 phases: checklist → dry-run → deploy → verify | N/A |
| `/autoresearch:scenario` | Generate edge cases across 12 dimensions | 20 |
| `/autoresearch:predict` | 5 expert personas debate before implementation | N/A |
| `/autoresearch:learn` | Scout codebase → generate docs or wiki → validate → fix loop | 10 |
| `/autoresearch:reason` | Adversarial debate with blind judges until convergence | 8 |
| `/autoresearch:probe` | 8 personas interrogate requirements until saturation | 15 |
| `/autoresearch:improve` | Research ICP challenges, discover improvements, generate PRDs | 15 |
| `/autoresearch:evals` | Analyze iteration results: trends, plateaus, regressions | N/A |
| `/autoresearch:regression` | Regression stability gate: baseline vs candidate, verdict STABLE/UNSTABLE | N/A |

### Subcommand routing

To run a subcommand yourself (an orchestrator hop or a `--chain` target), Read its protocol file and follow it:
`../../commands/autoresearch/<name>.md` (relative to this skill's directory), or `../../commands/autoresearch.md` for the classic loop.
The commands are user-typed only, so the model loads them from here instead of invoking them.

## Universal Flags

| Flag | Applies To | Purpose |
|---|---|---|
| `Iterations: N` | All looping | Set iteration count |
| `Iterations: unlimited` | All looping | Opt-in unbounded |
| `--evals` | All looping | Mid-loop checkpoints + final summary |
| `--evals-interval N` | All looping | Override checkpoint frequency |
| `--chain <targets>` | All | Sequential handoff after completion |
| `--<subcommand>` | All | Shorthand for `--chain <subcommand>` |
| `--dry-run` | Orchestrator | Print derived config + planned pipeline; no execution |
| `--max-cycles N` | Orchestrator | Hard ceiling on orchestration cycles (default 50) |
| `--classic` | Bare `/autoresearch` | Force Classic metric-loop mode |
| `--auto` | Bare `/autoresearch` | Force Orchestrator mode |
| `--no-fork` | Metric loops | Disable fork-and-flush rounds |
| `Forks: K` | Metric loops | Branches per fork-and-flush round (default 4; 2 when Verify is slow or uses a shared resource) |
| `Guided: R` | Metric loops | Fraction of fork branches given an Advisor-assigned experiment (default 0.5; 0 = all random) |

## Getting Unstuck: Fork-and-Flush

Metric loops run fork-and-flush rounds on a fixed schedule: at 33% and 66% of the budget, plus early when 5
iterations pass with no `keep`. A round forks K fresh-context branches from the best commit so far, runs each
for a small budget, and keeps the winner. A fresh context means the files and results log only, with none of
the leader's reasoning. Half the branches (by default) are random and pick their own ideas; the other half are
guided, each given one distinct experiment by a stateless Advisor that reads the results log. Protocol:
`references/fork-and-flush.md` (arXiv:2610.07447, arXiv:2610.07625).

## Orchestrator

Activated when a plain-language goal is given without `Metric:`/`Verify:`. Classifies the goal into a **Goal archetype** — see `references/orchestrator-routing.md` for the archetype table and router decision table.

Resolve every `scripts/...` path below relative to this installed skill directory, never relative to the caller's working directory.

For performance, latency, throughput, runtime, CPU, memory, allocations, binary
size, power, energy, bandwidth, or compute-cost goals, read
`references/behavior-preserving-optimization.md`. The working metric ranks
candidates; independent behavior evidence decides whether a candidate survives.

**Two modes based on archetype:**
- **Orchestration loop** — predicate-bearing archetypes (ship-ready, optimize-metric, fix-broken, harden, build-feature, explore). Goal has a mechanical Success predicate; the loop runs until that predicate is met.
- **Single-pass dispatch** — subjective/terminal archetypes (document, what-to-build, decide-design). Routes once to the fitting subcommand (learn / improve / reason), lets it self-terminate, then reports. No loop, no Plateau, no ship gate.

### Orchestration Loop Steps

Backed by `scripts/orchestrate.sh` (deterministic seam — all routing logic lives there). Subcommands exposed: `classify`, `next-hop`, `units`, `plateau`, `screen-cmd`, `verdict`, `validate-state`, `screen-state-predicate`.

1. **Classify** — `scripts/orchestrate.sh classify "<goal>"` → archetype label + mode.
2. **Derive predicate** — reuse `plan` logic to produce a concrete Success predicate: exact shell command + expected output. For `optimize-metric`, run the full plan/wizard derivation internally.
3. **Confirm** — ONE `AskUserQuestion` showing: archetype, mode, concrete predicate (command + expected output), terminal choice (stop-at-verified vs proceed-to-ship). Misclassifications are caught here, not mid-run.
4. **Round-0 dry-run** — prove the predicate command runs and returns a value; safety-screen every derived command via `screen-cmd`; print projected cycle budget. Stop here if `--dry-run`.
5. **Loop** until predicate satisfied:
   a. Assess state via cheap signals (last `handoff.json`, regression verdict, error count) + affected-test verify.
   b. `scripts/orchestrate.sh next-hop orchestrator-state.json` → next subcommand.
   c. Run subcommand via Subcommand routing (its own bounded inner loop).
   d. Record per-hop outcome ∈ {progressed, no-op, failed, blocked}.
   e. Fold hop's `handoff.json` into `orchestrator-state.json`.
   f. `scripts/orchestrate.sh units` → recompute **Units remaining** and append the number or `unknown` to the state's `units_remaining` array.
6. **Stop conditions** (checked after each hop):
   - Predicate met → ship gate (only if ship is in the pipeline) else `CONVERGED`.
   - Cycles > ceiling (default 50, override `--max-cycles N`) → stop + report `CEILING`. Checked first: a reached ceiling is never extended by fork rounds.
   - `scripts/orchestrate.sh plateau orchestrator-state.json` → exit 0 (flat): unless `--no-fork` or `fork_rounds_since_progress` is already 2, run one fork-and-flush round from the incumbent (`references/fork-and-flush.md`), add 1 to `fork_rounds_since_progress`, and continue; otherwise stop + report `PLATEAU`. Exit 1: continue. Exit 3: stop + report `BLOCKED`.
   - Hop outcome `blocked`/`failed` with no alternative route → checkpoint + stop + report `BLOCKED`.

### Orchestrator State

`orchestrator-state.json` — orchestrator-owned, additive. Tracks: goal,

토론

질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.

아직 글이 없어요. 처음으로 질문하거나 공유해 보세요.

이곳의 글은 사용자가 쓴 것으로, PopNx 팀의 글이 아니에요.

로그인하고 글쓰기

GitHub 정보

GitHub 스타
6,848
제작자
uditgoenka
라이선스
MIT
최근 코드 수정
2026년 10월 31일
repo 안 SKILL.md(번역본과 템플릿 포함)
5
토픽
ai, autonomous-agent, autoresearch, claude, claude-code, iteration, karpathy, productivity, skill