memory-factchecklisted

# Memory Fact-Check > Origin: the skill of the same name in [leeyudok/doksam-skills](https://github.com/leeyudok/doksam-skills). > **Deliberately forked** for template bundling — not auto-synced; good improvements are cherry-picked manually. Memory decays. A fact that was true when written becomes false as code, schema and infrastructure move on. **Stale memory is worse than no memory** — an agent reads it and confidently does the wrong thing. This is **not** a structural hygiene pass. Orphan files, duplicate entries, index bloat, broken internal links — those checks compare memory files *to each other*. This skill compares each memory **to the world it describes**: the code, the database, the issue tracker, the filesystem. A memory can be perfectly well-formed, correctly indexed, recently touched — and completely false. Automatic deletion is forbidden. Only a source-of-truth comparison can tell what is dead, and losing an incident lesson is expensive. Hence semi-automatic: **correct freely, archive only with approval, never delete.** ## 1. Locate and inventory Find the memory set. Common locations, in order: - a path declared by the project's agent instructions (`AGENTS.md` / `CLAUDE.md` — e.g. "memory SSOT is `.claude/memory/`"). A declared path wins over every default. - `.claude/memory/` in the repo (team-shared, committed) - the host's per-project memory dir (e.g. `~/.claude/projects/<slug>/memory/`) Collect for each file: frontmatter (`name`/`description`/`typ