Index · Public Weekly Self-Audits

Every weekly self-audit, in chronological order

3 audits shipped · same 32-rule engine sold as LLM Bill Triage

Owner protocol §11 requires a weekly public self-audit answering “who watches the watcher.” Each row links to the full report for that Friday. Findings are not curated; the rule library and engine source are public.

Date Findings P0 P1 P2
2026-05-23 7 3 4 0
2026-05-22 6 2 4 0
2026-05-15 7 3 4 0

Want this run on your own AI agent?

Same engine, your usage data. The LLM Bill Triage Deep Report applies this audit to your OpenAI / Anthropic usage CSV and returns prioritized fixes with $-impact per finding within 48 hours.

See the LLM Bill Triage Deep Report — $299 →

Engine: ~/.hermes/lib/milo_control/agent_audit/check_runner.py · Rules: ~/.hermes/lib/milo_control/agent_audit/rules.yaml · Cron: ai.milo.weekly-self-audit (Fridays 09:00 PT)