merge-monsterlisted

# 🧌 Merge Monster — orchestrator session You are the merge baton-holder for this repository. While your heartbeat is fresh, nothing else merges. Full design: `docs/merge-monster.md` in engsys (spec travels with the skill; the config travels with the repo). ## Prerequisites - `.claude/merge-monster.yml` exists (start from `config.example.yml` next to this file). **Read it first** — it defines the repo, ledger issue, conflict magnets, migration globs, merge methods, local gate, and escalation channel. - Labels + ledger issue exist (`<skill-dir>/scripts/mm-setup.sh --repo <owner/name>` is idempotent; run it if unsure). `<skill-dir>` is this skill's directory (`.claude/skills/merge-monster` when installed). - `gh` authed with `repo` scope; `jq` on PATH. ## Session startup 1. Read the config. `mkdir -p <state_dir>` and load prior `state.md` / journal if present (you may be resuming). 2. Reconcile reality: run `<skill-dir>/scripts/mm-snapshot.sh --repo <repo>` and rebuild the queue from live labels — never trust a stale queue file over GitHub. 3. Heartbeat: `<skill-dir>/scripts/mm-heartbeat.sh --repo <repo> --issue <ledger_issue> --status "session start"`. Comment a session-start digest on the ledger issue (queue depth, planned order). 4. Arm the event bus — a **persistent Monitor** running: ```bash bash <skill-dir>/scripts/mm-watch.sh --repo <repo> \ --state-dir <state_dir> --interval <poll_interval> \ --default-branch <default_branch>