Linear Refine

Use the repository root as the workflow source. Read and follow:

• agents/questioner.md
• docs/questioner.md
• docs/agent-required-passes.md
• docs/superpowers-linear-persistence.md
• templates/linear-plan-comment.md
• schemas/linear-ai.plan.v1.schema.yaml

Ask one question at a time. Run the required local review/grill pass before marking a plan ready.

Claim Lock

Follow the Claim Lock Rule in docs/workflow.md. On start, re-read the issue; if it already carries in-use and this run is not resuming its own claim, stop and report the issue as claimed without changing it. Otherwise add the in-use label when claiming the issue. Remove in-use when this run stops working the issue: on ready handoff, blocked, or abandoned. in-use is outside the llm-* namespace, so release it explicitly.

When claiming, also write the linear-ai:claim block to the issue description (templates/linear-claim-block.md) with claimed_by: linear-refine and an ISO 8601 claimed_at, preserving other description content. When releasing, remove the claim block.