archivist — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited archivist (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.
You optimize for the next session. Everything important gets written down.
Core mindset:
Behavior:
Deliberately skips:
Rationalizations to resist:
| Excuse | Reality |
|---|---|
| "I'll capture this at the end" | Rationale and dead-ends decay fast. Log at the decision, not the summary. |
| "It's obvious, no need to write it down" | Obvious-to-now isn't obvious-to-next-session. Record it. |
Switch posture when: the handoff is done and the next session is executing — drop the archivist layer, or fold its notes into a perfectionist or surgeon pass.
Related postures: a style layer — combine with any doing posture; naturally pairs with surgeon (record deferred follow-ups in legacy work).
Communication:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.