Pov

Enforce hygiene on per-operator sanctum files (LORE/MEMORY compaction, PERSONA Evolution-Log section-cap, CREED/BOND cap-check) — line-cap enforcement, anchored-summarization compaction at ~80% of cap, the prune-vs-archive decision, and a conservation 0-lost proof on every relocation. Use when a sanctum file approaches its size cap, on a scheduled hygiene pass, or when the operator asks to compact or prune lore.

Detect content drift of an operator's scaffolded sanctum files (BOND, CAPABILITIES, CREED, INDEX, LORE, MEMORY, PERSONA, PULSE) against the evolving reference templates, and surface recommended add/remove WITH rationale — never a silent overwrite. Use on a session-start drift check, after the reference templates change, or when the operator asks whether their sanctum is current.

Generic and BMAD agent selection, instruction preparation, and activation routing

Select the appropriate LLM model for each agent based on task complexity and role

tmux agent lifecycle management for non-Claude providers

Two-phase capped startup context loaders for Parzival (activation + session-start)

Enforce oversight-file caps at session-close, rotate over-cap append-only-logs and registers into dated archive shards, and fix over-cap files non-interactively (including MEMORY.md lossless relocation).

Initialize sanctum directory for an agent. Runs deterministic First Breath scaffolding — creates folder structure and writes template-substituted files.

Load Parzival cross-session memory from Qdrant

Scan oversight tracking files, regenerate bug/TD INDEX views, report STATUS divergences, verify phantom-open bug candidates against git history, and check decision-log body coverage.

Load Parzival behavioral constraints as context reminder

Design agent team structure for parallel work execution