autodev-parallel

autodev-parallel is a skill for Claude Code, Codex from jh941213/codex-lattice. It costs 90 tokens per session (1,686 once invoked), scanned A, original, MIT.

A parallel version of an autonomous development loop that gives independent PRD or checklist items to separate coding agents. Each agent works in an isolated worktree, which is a separate working copy of the repository.

In plain words
What is it for?
Use it for explicitly approved parallel experiments on independent development tasks, with configurable agent counts, rounds, file scope, and verification commands.
Why use it?
Independent tasks can be attempted at the same time while keeping their file changes separate. The results can then be checked and combined through cherry-picks.

Skill for Claude CodeCodex

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 skills/jh941213/codex-lattice/autodev-parallel
Any agent
npx skills add jh941213/codex-lattice --skill autodev-parallel
Clone the repo
git clone --depth 1 https://github.com/jh941213/codex-lattice

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for autodev-parallel

README.md
[![agentmods](https://agentmods.dev/badge/skills/jh941213/codex-lattice/autodev-parallel.svg)](https://agentmods.dev/skills/jh941213/codex-lattice/autodev-parallel)
Your own site
<a href="https://agentmods.dev/skills/jh941213/codex-lattice/autodev-parallel"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/autodev-parallel.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,686 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00090 $0.01686
Opus 5 $0.00045 $0.00843
Sonnet 5 $0.00018 $0.00337
Haiku 4.5 $0.00009 $0.00169

Measured 5d ago against content hash d2adef8be0a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autodev-parallel scanned grade A with 0 findings 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 5d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/autodev-parallel/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoDev Parallel — Codex /goal 병렬 오케스트레이터

사용자가 sub-agents 병렬 실행을 명시적으로 요청했을 때, 여러 Codex worker가 worktree 격리 환경에서 PRD 항목을 병렬 처리한다. 독립적인 항목들을 동시에 진행하여 완료 속도를 극대화. 장기 목표와 완료 조건은 Codex 내장 /goal에 두고, 이 스킬은 병렬 분류와 통합 전략만 담당한다.

핵심 개념

main (또는 현재 브랜치)
 │
 ├── worktree A ── Agent 1: PRD 항목 1
 ├── worktree B ── Agent 2: PRD 항목 2
 ├── worktree C ── Agent 3: PRD 항목 3
 │
 └── Orchestrator (이 스킬)
      - 독립 항목 분류 & 배정
      - 결과 수집 & 검증
      - cherry-pick으로 통합
      - 다음 라운드 반복

Phase 0: 설정 수집

goal: "무엇을 달성할 것인가"
done_when: "완료 판단 기준"
prd: "PRD 또는 체크리스트 파일 경로"     # 예: "PRD.md"
scope: ["수정 가능한 파일 패턴"]
verify: "검증 명령어"
parallel: 3                            # 동시 에이전트 수 (기본 3)
rounds: 5                             # 라운드 수 (기본 5)
max_iterations: 100                    # 명시적 재개 최대 반복 (기본 100)

시작 시 Codex 세션에 다음 목표를 설정한다:

/goal {goal}; done_when={done_when}; parallel={parallel}; verify={verify}; docs=docs/harness/*

Phase 1: 항목 분류

PRD를 읽고 항목들의 의존성을 분석:

## 독립 항목 (병렬 가능)
- [ ] 항목 A: API 엔드포인트 — src/api/
- [ ] 항목 B: UI 컴포넌트 — src/components/
- [ ] 항목 C: 테스트 작성 — tests/

## 의존 항목 (순차 필요)
- [ ] 항목 D: A 완료 후 → 통합 테스트

Phase 2: 라운드 루프

for round in 1..rounds:

  1. SELECT
     - 미완료 항목 중 독립적인 것 최대 {parallel}개 선택
     - 의존성이 있는 항목은 선행 항목 완료 후에만 선택

  2. LAUNCH (병렬)
     - {parallel}개의 Codex worker sub-agent를 동시에 호출
     - 각 worker는 별도 worktree와 명확한 파일 소유권을 갖는다
     - 각 Agent에게 전달하는 프롬프트:

     """
     PRD 항목을 구현하라.

     항목: {specific_item}
     Scope: {scope}
     Verify: {verify}

     절차:
     1. scope 내 파일을 읽고 항목을 구현
     2. {verify} 실행으로 검증
     3. 실패 시 build-fix 1회 시도
     4. 성공 시 git commit -m "[autodev] {item_summary}"
     5. 결과를 최종 메시지로 반환:
        AUTODEV_RESULT: status={success|fail}, commit={hash}, item="{desc}"
     """

  3. COLLECT
     - 각 Agent 완료 대기
     - 결과 파싱 (status, commit hash)

  4. INTEGRATE
     - 성공한 Agent의 변경사항을 cherry-pick
     - cherry-pick 충돌 시:
       - 충돌 해결 시도 (1회)
       - 실패 시 해당 항목 다음 라운드로 연기
     - PRD에서 완료된 항목을 [x]로 체크

  5. VERIFY ALL
     - 통합 후 전체 검증: {verify}
     - 실패 시 마지막 통합 커밋을 분리하고 사용자에게 상태 보고

  6. REPORT (라운드별)
     라운드 {round}/{rounds} 완료:
     - Agent 1: {status} — {item}
     - Agent 2: {status} — {item}
     - 남은 미완료 항목: {remaining}

  7. CHECK COMPLETION
     - 모든 항목 완료? → done_when 충족, docs/harness 갱신, `/goal clear`
     - 아니면 → 다음 라운드

Read the full file on GitHub · 175 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. 5d ago First seen · 175 lines · 90 tokens per session scan A d2adef8be0a4

Subscribe to this mod's changes

autodev-parallel is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,686 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens