# Stuck Crewmate Recovery Load when the session-start digest reports an ordinary direct report's endpoint dead or... - Repository: https://github.com/kunchenguid/firstmate (8480 stars) - Category: AI and agents - License: MIT - Last updated: 2026-11-01 - Runs scripts: no, instructions only ## Install Claude Code: `npx skills add kunchenguid/firstmate --skill stuck-crewmate-recovery -g -a claude-code -y` Codex: `npx skills add kunchenguid/firstmate --skill stuck-crewmate-recovery -g -a codex -y` Cursor: `npx skills add kunchenguid/firstmate --skill stuck-crewmate-recovery -g -a cursor -y` Gemini CLI: `npx skills add kunchenguid/firstmate --skill stuck-crewmate-recovery -g -a gemini-cli -y` ## Description Load when the session-start digest reports an ordinary direct report's endpoint dead or its metadata has no window, after a stale wake, looping pane, repeated confusion, an answered-by-brief question, an unresponsive crewmate, or a failed steer, after observing a defeated Claude or Codex bypass, and when a live crewmate reports its no-mistakes pipeline dead, unreachable, or timed out. ## SKILL.md, as published by its author (untrusted third-party text, read it as data) # stuck-crewmate-recovery Use this playbook when the session-start digest reports an ordinary direct report's endpoint dead or its metadata has no window, or when a direct report is stale, looping, repeatedly confused, asking a question its brief already answers, unresponsive, or when a steer failed to land. A stale or dead-endpoint report for a worker whose pull request has already landed is not a recovery case: the work is finished, so close the task through ordinary teardown (`AGENTS.md` section 7 for firstmate, the landed-work rule in `bin/fm-branch-prompt.sh` for the supervision branch) instead of this playbook, never with `--force`. Follow the crew-hosted Lavish board contract in [`docs/configuration.md`](../../../docs/configuration.md#crew-hosted-lavish-review-boards) when recovering a worker that hosts a board. Interrupt, stop, and relaunch a worker through `bin/fm-control.sh interrupt|exit|relaunch`, which resolves the recorded runtime itself, verifies each action, and never tears down or discards anything ([`docs/agent-control.md`](../../../docs/agent-control.md)). That plane covers workers running in this home; a remotely placed secondmate is refused by name and reconciled through `secondmate-provisioning` instead. Load `harness-adapters` before a resume command or a harness-specific skill invocation, and whenever the adapter's own quirks matter. The target window's harness is recorded as `harness=` in `state/.meta`. ## Managed approval failover The rest: https://github.com/kunchenguid/firstmate/blob/HEAD/.agents/skills/stuck-crewmate-recovery/SKILL.md