autodev

autodev is a skill for Claude Code, Codex from jh941213/codex-lattice. It costs 94 tokens per session (1,743 once invoked), scanned A, original, MIT.

An autonomous development loop for working through a product requirements document, or PRD, one checklist item at a time. It records progress, verification results, and possible commits while using Codex goals to track when the work is complete.

In plain words
What is it for?
Use it to process a PRD or task list, run the project’s tests or another verification command, and keep logs of completed work and commit candidates.
Why use it?
It gives long-running implementation work a repeatable process and clear stopping conditions. Each item is checked before the loop moves on.

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
Any agent
npx skills add jh941213/codex-lattice --skill autodev
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

README.md
[![agentmods](https://agentmods.dev/badge/skills/jh941213/codex-lattice/autodev.svg)](https://agentmods.dev/skills/jh941213/codex-lattice/autodev)
Your own site
<a href="https://agentmods.dev/skills/jh941213/codex-lattice/autodev"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/autodev.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,743 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 $0.00094 $0.01743
Opus 5 $0.00047 $0.00872
Sonnet 5 $0.00019 $0.00349
Haiku 4.5 $0.00009 $0.00174

Measured 5d ago against content hash 40ec406b66ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autodev 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/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoDev — Codex /goal 자율 개발

Codex용 자율 개발 루프. PRD/체크리스트의 항목을 하나씩 완료하고 검증 가능한 커밋 후보를 만든다. 장기 목표와 중단 조건은 Codex 내장 /goal에 둔다. 하네스는 진행 문서, 검증 로그, 커밋 후보 로그를 보강한다.

핵심 원리

/goal 설정 → PRD 읽기 → 다음 항목 처리 → 검증 → 커밋 후보 로그
                                                      ↓
                                             done_when 충족?
                                              ↓ Yes       ↓ No
                                         /goal clear   /goal 유지 후 재개

Phase 0: 설정 수집

사용자에게 확인 (빠진 것만 질문):

goal: "무엇을 달성할 것인가"           # 예: "PRD.md의 모든 항목 완료"
done_when: "완료 판단 기준"            # 예: "PRD의 모든 체크박스 완료 + npm test 통과"
prd: "PRD 또는 체크리스트 파일 경로"    # 예: "PRD.md" 또는 "tasks/todo.md"
scope: ["수정 가능한 파일 패턴"]        # 예: ["src/**", "tests/**"]
verify: "검증 명령어"                  # 예: "npm test" (자동 감지 가능)
max_iterations: 100                   # 최대 반복 수 (기본 100)
mode: "continue"                      # continue | reset (기본 continue)

verify 자동 감지

사용자가 verify를 안 줬으면:

  1. package.jsonnpm test 또는 vitest run
  2. pyproject.tomlpytest
  3. Makefilemake test
  4. 없으면 → echo "no verify command"

Phase 1: 루프 초기화

Codex 세션에서 먼저 목표를 설정한다:

/goal {goal}; done_when={done_when}; scope={scope}; verify={verify}; docs=docs/harness/*
# 1. autodev 브랜치 생성
git checkout -b autodev/$(date +%Y%m%d-%H%M)

# 2. .codex-lattice/autodev/ 상태 디렉토리 생성
mkdir -p .codex-lattice/autodev

# 3. 상태 파일 초기화
cat > .codex-lattice/autodev/state.json << 'STATE'
{
  "active": true,
  "iteration": 0,
  "max_iterations": {max_iterations},
  "prompt": "{goal}",
  "done_when": "{done_when}",
  "prd_path": "{prd}",
  "verify_command": "{verify}",
  "started_at": "{ISO시간}",
  "status": "running"
}
STATE

# 4. .gitignore에 .codex-lattice/autodev/ 추가
echo ".codex-lattice/autodev/" >> .gitignore

# 5. 베이스라인 검증
{verify} 2>&1 | tee .codex-lattice/autodev/baseline.log

Phase 2: 반복 실행 (매 세션)

각 세션(반복)에서 수행하는 절차:

1. READ PRD
   - {prd} 파일을 읽는다
   - 미완료 항목([ ]) 중 첫 번째를 선택

2. PLAN
   - 선택한 항목을 구현하기 위한 최소 변경 계획
   - scope 내 파일만 수정 가능

3. IMPLEMENT
   - 계획대로 코드 수정
   - scope 밖 파일 절대 수정 금지

4. VERIFY
   - {verify} 실행
   - 실패 시 build-fix 1회 시도
   - 2회 실패 시 작업 중단, diff와 실패 원인을 기록
   - 파괴적 롤백은 사용자 승인 없이 실행하지 않음

5. COMMIT
   - 성공 시:
     git add [specific-files]
     git commit -m "[autodev] {항목 요약}"
     .codex-lattice/commits/에 후보 로그 확인
   - PRD에서 해당 항목을 [x]로 체크

6. CHECK COMPLETION
   - PRD에 미완료 항목이 남아있는가?
   - Yes → `/goal`을 유지하고 다음 반복을 명시적으로 재개
   - No → done_when 충족. `docs/harness/`와 검증 결과를 갱신하고 `/goal clear`

Read the full file on GitHub · 186 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 · 186 lines · 94 tokens per session scan A 40ec406b66ce

Subscribe to this mod's changes

autodev is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 1,743 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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