A police department for your Claude Code agents
Hash-chained audit log catches agent violations at zero token cost.
A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule offenses (permission bypass, out-of-scope & credential access, self-permissioning, disallowed tools, redundant, off-task) with quoted evidence. Catch-and-report, never blocks.
Catches denied calls that never reach transcripts—six detectors at zero token cost.
Developers running Claude Code agents who need audit trails
Waldo · AgentOps · LangSmith
Hash-chained audit log catches agent violations at zero token cost.
Dead man's switch plus spend controls solve a real AI agent safety gap nobody else addresses.
Runs with one npx command and immediately surfaces a helpful timeline view with token counts, tool I/O panes and subagent nesting — exactly the sort of visibility you want when an agent goes off the rails. Cleverly reads the local ~/.claude/projects traces so setup is trivial, but its usefulness is limited by being Claude-only and local; add search/aggregation or a team-sharing mode and this jumps up a tier.
Agent approval gates and audit logs beat open-source alternatives, but multi-agent governance isn't novel.
AI trading harness with approval boundaries and audit logs for Claude agents.
Finally, a tool that tells you why your AI coding bill is exploding.