Back to browse
GitHub Repository

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.

16 starsPython

Agent-pd – A zero-token audit log to catch rogue Claude Code subagents

by softie123·Jun 9, 2026·6 points·2 comments

AI Analysis

●●SolidBig BrainNiche Gem

Catches denied calls that never reach transcripts—six detectors at zero token cost.

Strengths
  • Deterministic detectors catch violations without burning tokens on LLM analysis.
  • Hash-chained tamper-evident logs with optional off-host append-only storage.
  • Covers main agent plus all subagents including dynamic Workflow spawns.
Weaknesses
  • Logging-only approach can't block actions, only report after the fact.
  • Niche audience limited to Claude Code users concerned about agent behavior.
Category
Target Audience

Developers running Claude Code agents who need audit trails

Similar To

Waldo · AgentOps · LangSmith

Similar Projects

Developer Tools●●Solid

A police department for your Claude Code agents

Hash-chained audit log catches agent violations at zero token cost.

WizardryNiche Gem
softie123
11810d ago
Developer Tools●●Solid

Npx Claude-traces, visualizer for Claude Code/Agent SDK traces

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.

Niche GemSolve My ProblemSlick
hahawhatsgood
204mo ago
AI/ML●●Solid

Axon – Agentic AI with mandatory user approval and audit logging

Agent approval gates and audit logs beat open-source alternatives, but multi-agent governance isn't novel.

Solve My ProblemBig Brain
NeuroVexon
124mo ago