autolinear
Autonomous Linear to Claude Code bridge. Picks up issues labelled @autolinear, routes them to agents by tag, captures proof-of-work, and drives each issue from Todo to Done with reviewer feedback loops. Alpha: manual /autolinear:run is end to end; webhook pickup stops at a dispatch stub.
| Version | 0.4.1 |
| Marketplace | magus-alpha |
| Commands | 5 |
| Subagents | 3 |
| Skills | 4 |
| MCP server | no |
| Hooks | yes |
Install
claudeup
Find autolinear on the Plugins tab and turn it on. claudeup registers the magus-alpha
marketplace if you do not have it, and installs what the plugin needs to actually run —
binaries, MCP servers, CLI tools.
For a team, press s to save your plugins as a profile and commit it. Everyone else runs
claudeup install — see Teams and profiles.
Prefer to do it by hand? Installing Magus has the manual path.
When to reach for it
- Use when a reviewer has commented on an autolinear issue and the work needs another pass —
feedback-processor
Commands
| Command | What it does |
|---|---|
/autolinear:autolinear-config | Configure Linear integration settings for autolinear |
/autolinear:autolinear-create-task | Create a Linear task from CLI and assign to autolinear for execution |
/autolinear:autolinear-help | Show comprehensive help for the AutoLinear plugin |
/autolinear:autolinear-run | Manually trigger execution of a specific Linear task |
/autolinear:autolinear-status | Check autolinear status, queue, and task progress |
Subagents
Dispatched with the Agent tool, each in its own context window.
| Agent | What it does |
|---|---|
autolinear:feedback-processor | Reads Linear comment feedback on an in-flight task and turns it into a concrete revision plan. Use when a reviewer has commented on an autolinear issue and the work needs another pass. |
autolinear:proof-generator | Generates proof-of-work artifacts — diffs, test output, screenshots — that show a Linear task was actually done. |
autolinear:task-executor | Executes a picked-up Linear issue end to end, reasoning and acting in a loop until the acceptance criteria are met. |
Skills
| Skill | What it covers |
|---|---|
autolinear:linear-integration | Linear API patterns and examples for autolinear. Includes authentication, webhooks, issue CRUD, state transitions, file attachments, and comment handling. |
autolinear:proof-of-work | Proof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence scoring. |
autolinear:state-machine | Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs. |
autolinear:tag-command-mapping | How tag-to-command routing works in autolinear. Defines default mappings, precedence rules, and customization patterns. |
Hooks
This plugin installs hooks. They run automatically and are the usual first place to look if its behaviour stops firing.
Source
plugins/autolinear/ on GitHub, including its full README.