compaction-survival

Maintain a persisted, re-readable control anchor so a long autonomous run survives context compaction without losing the plot — one file holding the mission, a plan pointer, a live cursor (done / in progress / next action), invariants, last-known-good state, and exact resume steps, updated after each step and re-read at the start of each turn. Use when starting or driving a multi-hour or multi-phase autonomous task, a self-driving loop, or any unattended run that will cross one or more automatic compactions or context-window resets; on asks like "make sure compaction doesn't lose the work", "keep state across auto-compact", "persist the current state so a reset doesn't disrupt this", "this is a long autonomous run", or "resume cleanly after a reset". The anchor is intra-actor state recovery — the same actor re-reading its own working state across a discontinuity. Not for handing work to a fresh context or a teammate (that is context-handoff's inter-actor brief), not for post-hoc capture of what a finished session learned (that is journaling-sessions), and not for tracking a short task that fits comfortably in one context window. The /anchor command is the one-off snapshot entry point; when the running session lacks the plugin surface entirely (stale snapshot, harness without the skill menu), references/cold-start.md has the by-hand recipe.