memory-hygiene — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited memory-hygiene (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
memory-hygiene 是 manual memory tiering：檢查 Hot / Warm / Cold，產生 demotion candidate，並在使用者確認後搬移 memory files 與更新 index。
這是 memory maintenance skill，不是一般 task planning。Scan / dry-run 只讀；apply 會寫 workspace memory，因此必須先有本 session 的 dry-run 結果與使用者明確確認。
| User says | Mode | Reference |
|---|---|---|
/memory-hygiene, memory-hygiene, default | scan | memory-hygiene-scan-flow.md |
dry-run, full report, 看看所有分類 | dry-run | memory-hygiene-scan-flow.md |
apply, 搬檔, 執行, migrate | apply | memory-hygiene-apply-flow.md |
| Situation | Load |
|---|---|
| Any run | polaris-project-dir.md, feedback-memory-procedures.md |
| Scan / dry-run | memory-hygiene-scan-flow.md |
| Apply | memory-hygiene-apply-flow.md |
Classification rules live in scripts/memory-hygiene-tiering.py and rules/feedback-and-memory.md Memory Tiering.
Plan artifact authority lives in bash scripts/validate-memory-hygiene-plan.sh。 apply 不應直接吃任意 JSON；必須先通過 plan validator。
dry-run --json | validate-memory-hygiene-plan.sh | apply；不要手動改 plan JSON 後直接餵 apply。MEMORY_HOT_CAPACITY env 可覆寫）：超量者依確定性 ranking 自動降 Warm，pinned + graduated_to 永遠不被擠出，migration log 列出 overflowed-hot-capacity 降級檔名。chain 在含 nested_frontmatter 的 plan 也能跑通； validator 把 nested_frontmatter 移到 warnings，apply 內部 normalize 是唯一 enforcement path，不需要 POLARIS_MEMORY_HYGIENE_APPLY=1 bypass。
Return mode, memory dir, Hot/Warm/Cold counts when available, candidate summary, apply status, files moved, migration log path, and any anomalies.
Execute post-task-reflection-checkpoint.md before reporting completion.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.