← ClaudeAtlas

gh-issue-claim-coordinationlisted

Coordinate GitHub issue pickup across parallel Claude Code sessions (or human + agent) using BOTH `assignees` and a `wip` label, so sibling sessions detect the claim and skip. Use BEFORE writing any code that closes / addresses a GitHub issue when there's any chance another session is working the same repo. Trigger on phrases like "pick up issue
wan-huiyan/agent-traffic-control · ★ 2 · AI & Automation · score 73
Install: claude install-skill wan-huiyan/agent-traffic-control
# GitHub issue claim coordination (assignee + label) When multiple Claude Code sessions (or human + agent) work the same repo in parallel, two sessions can independently pick up the same issue, do parallel implementations, and collide at PR time — burning hours of duplicated work and forcing one branch to be rebased or abandoned. **Default agent behaviour is silent.** An agent dispatched to "work on the bug-tagged issues" does not automatically check whether another session is already on issue #N. There's no built-in coordination unless this skill (or equivalent) runs at pickup. This skill installs a 60-second protocol — preflight check, atomic claim, stale-claim sweep, release on completion — using two GitHub-native primitives so the claim is visible everywhere (issue list UI, `gh issue list`, dashboards, sibling sessions). ## Why both `assignee` AND a `wip` label? They cost ~0 to set together and cover different failure modes: - **`assignees`** is GitHub's canonical "who's on this" primitive. `gh issue list --assignee ""` cleanly enumerates unclaimed work; agents tend to surface assignees in their own context without prompting. - **A `wip` label** is far more visible in the GitHub issue list UI (a coloured chip next to the title) and lets you find every active claim with one query: `gh issue list --label wip`. It also survives the case where someone reassigns the issue without thinking about coordination. Belt and suspenders. If the assignee gets dropped on a bulk ed