autodev
Skill0 starsChanged 3 months agoMITView on GitHub
Launch, monitor, resume, or stop a fully autonomous autodev pipeline run (spec → analyze → implement → verify → push → review → test → deploy in an isolated git worktree, live on the Mission Control dashboard), scaffold a repo's mission and factory rules, or run the issue-queue daemon. Use when the user says "/autodev", "autodev run <requirement>", "start a pipeline for X", "autodev status", "resume run N", "stop run N", "autodev init", or "start the autodev daemon".
- Installs packages
5 other projects use a version of this.
Adopted by
Most recently taken up by
- envestcc/autodevtheir own version, first seen Oct 15, 2026
- ominou5/agentic-workflowstheir own version, first seen Oct 13, 2026
- Momoyeyu/autodevtheir own version, first seen Oct 10, 2026
- Momoyeyu/skillstheir own version, first seen Oct 10, 2026
- DanaResearchGroup/agent-skillstheir own version, first seen Aug 26, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- Momoyeyu/autodev★ 8same name
- Momoyeyu/skills★ 8same name
- DanaResearchGroup/agent-skills★ 1same name
- envestcc/autodev★ 1same name
- ominou5/agentic-workflows★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- speckit-analyzeSkill
- speckit-checklistSkill
- speckit-clarifySkill
- speckit-constitutionSkill
- speckit-convergeSkill
- speckit-implementSkill
- speckit-planSkill
- speckit-specifySkill
- speckit-tasksSkill
- speckit-taskstoissuesSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
All commands run from any directory via the globally-installed autodev command (npm install -g github:rohitgupta2432/claude-autodev).
- Distinctive: line 53
Never re-implement pipeline stages yourself — the runner owns them.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- Confirm the target repo:
--repo <path>argument, else the current working directory (must be a git repo — verify withgit rev-parse --git-dir). - Run:
autodev run "<requirement>" --repo <path>(from a GitHub issue instead:autodev run --issue <n> --repo <path>) - 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.
Set up a repo
autodev init --repo <path>scaffolds.autodev/mission.md(goals and non-goals — the only thing that lets a run be REJECTED as out of scope) and.autodev/factory-rules.md(constraints binding on unsupervised sessions). Both are templates: tell the user they must edit them, and that an empty non-goals list means nothing is ever out of scope.- Stage 8 (Deploy) is opt-in per repo via
"deploy"in.autodev.json. Never add it on the user's behalf without asking — it merges and deploys with no human in the path.
Run the queue
autodev daemon --repo <path> [--interval 30] [--max-parallel 2] [--auto-accept] [--once]reconciles finished runs onto their issues, then starts runs for issues labelledautodev:accepted.--auto-acceptlabels untriaged issues automatically. Only suggest it for a private repo, and say plainly that it lets any issue filed there start a run.- It runs in the foreground until stopped;
--oncedoes a single tick.
Other commands
- Status:
autodev status - Resume a BLOCKED run:
autodev resume <id>(first read~/.autodev/runs/<id>/blocked.mdand summarize the diagnosis to the user) - A REJECTED run is a decision, not a failure — it means the spec stage judged the requirement against the repo's mission and declined it. Do not resume it; report the reason and ask whether to narrow the requirement or edit the mission.
- Stop:
autodev stop <id>
Never re-implement pipeline stages yourself — the runner owns them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.