resumelisted
Install: claude install-skill spacegrowth/claude-relay
Run: `${CLAUDE_PLUGIN_ROOT}/bin/relay resume $session_id` (Claude Code substitutes the plugin's
absolute path when this skill loads — call it this way, not as bare `relay`, which often isn't on
the Bash tool's non-interactive PATH).
This opens a fresh iTerm tab running `claude --resume <the executor's Claude session id>` in its
worktree, so the executor comes back with its **entire conversation/context** and the worktree's
**staged work intact**, and picks up its packet where it left off. Prefer this over `/relay:restart`
whenever you want to keep what the executor already did.
Requires the Claude session id captured at spawn — only sessions spawned after that capture landed
have it. If relay says there's no captured id, use `/relay:restart` instead (re-runs the packet as
a fresh session, losing prior context). If the session still looks alive, relay refuses unless you
pass `--force` (avoid two live instances of the same conversation).
**Ownership follows the resume.** Resuming an executor also **adopts** it — re-points its auto-wake
to the acting lead — which matters after a handoff (an inherited executor otherwise keeps waking
its old, retired lead, silently, forever). If it's currently owned by a live *other* lead, relay
warns instead of stealing it; `relay adopt <session_id> --force` takes it explicitly.
**Restoring a crashed lead.** `/relay:resume <session-id>` also brings back a **crashed lead** — pass
the lead's session id (find it in the LEADS section of `/relay:l