queue-next

Topics in the source

• queue-next
• When to load
• The loop
• Scoping
• Gotchas

Picks the next unblocked task from the repository's task graph, claims it so no other agent takes it, and runs the worker loop — optionally scoped by tags, a workspace, a capability or a fuzzy title. CANARY: queue-next-loaded-2026-06-13-fb78d23e-b2c3d4e5f6a7b8c9 The user types /queue-next, "continue", "resume", "run the workers", or WORKSPACE: Continue (equivalent to /queue-next WORKSPACE). A session needs to pick up where a previous one left off. 1. Fetch the task issues as claude-arsenal/AGENTS.md session-start steps 1–2 say (no body). Add statereason where the surface returns it: without it, a closed issue reads as done unless it carries arsenal:cancelled. 2. Ask for the next task. One call, one line of output: taskselect.py (in claude-arsenal/scripts/) applies deps, priority, capabilities and scope. It reads arsenal/session/surfaceprofile.json itself; add --capability access:browser when a browser appears in this session's own tools — the probe sees the machine, not the session's connectors. gate: false in its output means the task has no runnable gate; fix the task file before working it, since a prose gate checks nothing. 3. Check nobody else holds it. Read the task's issue a

This is an excerpt. Refer to the complete source and its current requirements.