# Autodev

> Launch, monitor, resume, or stop a fully autonomous autodev pipeline run (spec → analyze → implement → push → review → test in an isolated git worktree, live on the Mission Control dashboard). Use when the user says "/autodev", "autodev run <requirement>", "start a pipeline for X", "autodev status", "resume run N", or "stop run N".

- Skill: `rohitguta2432/autodev` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rohitguta2432/autodev`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rohitguta2432/autodev/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: rohitguta2432 (https://skillmd.com/u/rohitguta2432)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rohitguta2432/autodev

---


# autodev — autonomous pipeline

All commands run from any directory via the globally-installed `autodev` command
(`npm install -g github:rohitgupta2432/claude-autodev`).

## Start a run
1. Confirm the target repo: `--repo <path>` argument, else the current working
   directory (must be a git repo — verify with `git rev-parse --git-dir`).
2. Run: `autodev run "<requirement>" --repo <path>`
3. Relay the output to the user: run id, branch, worktree, dashboard URL
   (http://127.0.0.1:4590/). That's all — the run is fully autonomous.

## Other commands
- Status: `autodev status`
- Resume a BLOCKED run: `autodev resume <id>`
  (first read `~/.autodev/runs/<id>/blocked.md` and summarize the diagnosis to the user)
- Stop: `autodev stop <id>`

Never re-implement pipeline stages yourself — the runner owns them.