janwilmake

Linear Orchestrator — Development skill for Claude Code

Development community

Claude Code skill: an unattended nightly loop that turns Linear tickets into reviewed PRs.

How to install Linear Orchestrator

This entry records only its repository, not the path inside it, so there is no exact command to give. Open janwilmake/linear-orchestrator and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Linear Orchestrator does

Claude Code skill: an unattended nightly loop that turns Linear tickets into reviewed PRs.

Alternatives in Development

Evo — turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run 1.4k ★
Continuous Claude — Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging 1.3k ★
Ctf 24h Fleet — 24h unattended multi-target Web CTF fleet loop runner 1.1k ★

README

Linear Orchestrator

**Tickets in. Reviewed pull requests out. Nobody watching.**

A [Claude Code](https://claude.com/claude-code) skill that runs your Linear board overnight and hands you a morning of pull requests to read.

There is an experimental second generation, [linear-orchestrator2](https://github.com/janwilmake/linear-orchestrator2), which moves the whole conversation — body, screenshots, review, steering — into the Linear ticket. This repo is the maintained generation: the conversation lives on the pull request, and you steer by commenting there.

![How it works: you write a ticket, the gate waits for free memory, agents write the code, a fresh agent reviews it, and you get a PR to read](./hero.svg)

![The nightly factory: a ticket flows in from Linear, through the gate, a coding agent that opens a full-bodied draft PR, and a fresh reviewing agent, and a reviewed ready PR flows out to GitHub — where the conversation lives, and your comment becomes tomorrow's ticket](./demo.gif)

What makes it different

**The whole interface is two surfaces.** A ticket in Linear, and a comment on a pull request. There is no chat window to steer, no label to remember, no plan to approve inside the tracker. To change the direction of the work you comment on the PR, and the loop reads it, answers it by name, and acts on it. That works on a **merged** PR too, which is where it earns its keep: merge, note the follow-up work the PR spotted but left out of scope, and the loop turns your note into the next ticket by itself. Teammates can steer it the same way, on purpose.

**Draft means something.** A PR leaves draft only on evidence — a review, a fix pass over that review, a screenshot when a user can see the change, no merge conflict, and CI green on the head commit. It never leaves draft on an agent's say-so. So what is not a draft in the morning is what is actually ready, and the drafts are the pile you can ignore until you have time.

**Idle costs nothing.** N