Menu
How to keep memory clean. Archive stale daily logs. Promote important findings to long-term memory. Remove contradictions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Complete reference for the factory CLI — all commands, arguments, options, and usage. Use when an agent needs to invoke factory commands, check correct syntax, or understand available options.
When and how to write a human-action-needed entry to memory/{agent}/needs.md. Agents write these entries when they hit blockers that only a human can resolve.
When you encounter a failure, correction, or new pattern, write a learning and optionally propose a skill.
How the factory workspace is organized and what each directory means.
What to examine during a reflection pass and how to write observations to memory/{agent}/needs.md.
When and how to write scenario holdouts for factory verification.
| name | memory-hygiene |
| description | How to keep memory clean. Archive stale daily logs. Promote important findings to long-term memory. Remove contradictions. |
Daily logs in memory/daily/{agent}/ are append-only during the day. Librarian's
job is to prevent them from becoming a graveyard of stale entries.
On each heartbeat:
memory/daily/{agent}/archive/)memory/{agent}/MEMORY.md is the agent's curated, durable memory. Promote to it:
Do NOT promote:
memory/shared/KNOWLEDGE.mdWhen reviewing memory/shared/KNOWLEDGE.md or individual agent memories, watch for:
When a contradiction is found, determine which version is more authoritative, update to reflect it, and note the resolution in your daily log.
When reviewing skills/proposed/: check for redundancy against existing skills, verify
actionability, and confirm scope. Do not promote duplicates — note the duplication in
the proposing agent's memory.