unitares-governancelisted

# UNITARES Governance This umbrella skill exists for backward compatibility and as a stable top-level entrypoint into the UNITARES framework. ## Core Model UNITARES evaluates agent state with the **EISV** model: - `E`: effective energy / execution drive - `I`: information integrity / calibration - `S`: entropy / drift / instability - `V`: valence (signed E-I imbalance) EISV is proprioceptive state estimation, not an outcome oracle. The public `coherence` field is producer-dependent; the deployed `legacy_tanh_v` value is ODE control feedback. It still participates in configured check-in compatibility backstops, but it is not behavioral health evidence and no longer authorizes recovery. Agents typically call `start_session(force_new=true)` once for a fresh process identity, then continue that same running process with `sync_state()` as their main check-in loop. A new user message is not a reason to call `start_session(force_new=true)` again; that mints another process identity. These are the primary workflow tools; raw implementation tools such as `onboard(...)` and `process_agent_update(...)` remain available for compatibility. The full raw payload remains available under `raw_governance`; the read aliases `check_working_state` and `search_shared_memory` default compact and require their documented full-mode option to include it. ## Session Continuity Use `start_session(force_new=true)` to register a fresh process identity once. If the process is a deliberate handoff c