Persistent Memory Three Layer Drift Control 20260812 v1.0
What It Does
Persistent Memory Three Layer Drift Control helps teams audit memory designs across working, session, and durable layers. It turns redacted notes into a drift-control report covering ownership, promotion, retention, source references, contradiction checks, regression checks, and rollback plans.
The skill is advisory and read-only. It does not edit memory, promote records, delete content, or change agent state.
Use Cases
- Agent operators designing persistent memory governance before rollout.
- Reviewers checking whether memory promotion and retention rules are documented.
- Teams that need drift, contradiction, regression, owner, and rollback evidence in one report.
Requirements
- Python 3 with standard-library modules only.
- Redacted memory-design notes supplied by
--notesor--text. - No API keys required.
- OpenClaw workspace capable of running local skill scripts.
Example Usage
python3 scripts/persistent_memory_three_layer_drift_control.py --text "working memory defined; session memory defined; durable memory defined; promotion rule documented; retention rule documented; contradiction check present; rollback plan present" --json
Expected output is JSON containing a deterministic status such as PASS, REVIEW, BLOCKED, or ERROR, evidence coverage, findings, and mutated_files: [].
Price
$4.99