fulcra-agent-continuity

# Fulcra Agent Continuity Enhances the [`fulcra-agent-teams`](https://github.com/fulcradynamics/agent-skills) skill. Teams already uses `member/<agent>/progress.md` to survive isolated cron/heartbeat runs, but it's freeform — a fresh session has to re-read prose and guess what mattered. This skill adds a **structured** snapshot (objective, decisions, next actions, open questions, artifacts, context-used-%) and a **deterministic resume brief**, so waking up is reliable instead of a re-read. Whether/when to snapshot is a judgment call (prose); building the schema and folding many snapshots to the newest is deterministic (the `coord-engine` tool). ## The lifecycle contract (applies on every harness) Any agent participating in a team space owes these four behaviors. Harness adapters (see fulcra-agent-automation §Harness adapters) automate them where the platform allows; where it doesn't, follow them as prose: 1. **On wake** (new session, cron fire, heartbeat, automation tick): `coord-engine continuity resume <team> <agent>` and read your inbox (`coord-engine inbox <team> --agent <agent>`) BEFORE taking new work. 2. **On material change** (a decision made, an artifact produced, a task claimed or finished) and at least hourly while actively working: `coord-engine continuity snapshot <team> <agent> <task> --objective … [--decision …] [--next …]`. 3. **Before context loss** (compaction, model handoff, session end): `coord-engine continuity park <team> --agent <age...