Model Fingerprint Audit Skill
Audit OpenAI-compatible or Anthropic-compatible model endpoints using repeated behavioral probes, stability metrics, and reference fingerprints. Use when checking whether a proxy model is stable or plausibly matches its claimed identity.
as observed 2026-10-05T10:33:23.015Z- Identifier
model-fingerprint-audit- Source
- ClawHub
- Version observed
- 1.0.3
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-10-04T09:46:17.065Z
- Observations recorded
- 2
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 89
- Declared license
- MIT-0
Observation history
2026-10-05T10:33:23.015Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Add Coding Plan versus PaaS resource separation, 1113 handling, and safe community contribution rules." | "Add baseline caching: collect trusted reference once, reuse locally for routine audits, and refresh only on version or drift conditions." |
latestVersion |
"1.0.2" | "1.0.3" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.