Individual skill

memory-hygiene

Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against the live environment, stamps last_verified + confidence, and proposes archiving drifted entries

skills/memory-hygiene/SKILL.md

Read pinned source

Source commit 144c7a3a959cc99538b7dfee9c22c4b065a0e156

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 1,370
Repository last updated: Oct 23, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agentic Repository topic
ai-agents Repository topic
claude-code Repository topic
cursor Repository topic
garry-tan Repository topic
gbrain Repository topic
gstack Repository topic
knowledge-management Repository topic
obsidian Repository topic
productivity Repository topic
productivity Derived category
productivity-notes Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,874 bytes

Read excerpt


# COG Memory Hygiene Skill

## Purpose

Prevent the **stale-but-confident** failure mode: a memory or knowledge note that was correct when written ("the webhook lives at X", "the board ID is Y") silently drifts after the environment changes, yet still ranks high at recall and gets acted on.

The system move (adapted from "From Model Scaling to System Scaling: Scaling the Harness in Agentic AI", Gu, UC Berkeley, arXiv:2605.26112): **make trust a runtime decision, not a property of the stored item**. Re-verify against the live environment, and keep per-entry `last_verified` and `confidence` as first-class fields so future recalls can weigh trust.

## When to Invoke

- `/memory-hygiene`
- "Audit my memories" / "check for stale memories"
- After a memory misfires (a recalled fact turned out wrong)
- Default cadence: monthly