# Claw Lens

## Docs

- [Audit Rules](https://claw-lens.com/audit/audit-rules.md): Reference for all built-in detection rules active in the Security Audit engine.
- [Credential Inventory](https://claw-lens.com/audit/credential-inventory.md): View and manage all credential and secret exposures detected across agent sessions.
- [Security Audit](https://claw-lens.com/audit/overview.md): Scan every agent session for credential exposure, dangerous shell commands, prompt injection, and behavioral anomalies.
- [Risk Scoring](https://claw-lens.com/audit/risk-scoring.md): How Claw Lens assigns risk levels to agent events, and what each level means.
- [Cache Trace](https://claw-lens.com/debugging/cache-trace.md): Debug prompt cache misses at the API-call level with pipeline flow visualization and diff between consecutive calls.
- [Context Breakdown](https://claw-lens.com/debugging/context-breakdown.md): Visualize how system prompt, conversation history, and tool results fill your agent's context window at every step.
- [Deep Turns](https://claw-lens.com/debugging/deep-turn.md): Surface turns with abnormally deep tool-call sequences to spot where your agents are struggling or stuck in loops.
- [Tool profiler](https://claw-lens.com/debugging/profiler.md): Aggregate tool call performance across all sessions or a single session. Find slow tools, high error rates, and duration distributions at a glance.
- [Session timeline](https://claw-lens.com/debugging/session-timeline.md): Inspect every LLM turn and tool call in a Gantt-style chart. Drill into token counts, latency, and raw tool I/O for any session.
- [Development](https://claw-lens.com/development.md): Clone the repo and run Claw Lens from source in development or production mode.
- [Agent Observability](https://claw-lens.com/engineering/agent-observability.md)
- [Design Doc](https://claw-lens.com/engineering/design-doc.md): System architecture, design principles, technical choices, and intentional trade-offs behind claw-lens.
- [Agents](https://claw-lens.com/monitoring/agents.md): The Agents page shows one card per OpenClaw agent with health status, current task, error rates, cache hit rates, cost data, and a 7-day activity breakdown.
- [Cron jobs](https://claw-lens.com/monitoring/cron-jobs-copied-1.md): Monitor scheduled OpenClaw agent tasks — see next run times, last run status, consecutive error counts, and full run history.
- [Live Monitor](https://claw-lens.com/monitoring/live-monitor.md): The Live Monitor shows every active OpenClaw agent session in real time, with step-by-step traces of what the agent is doing right now.
- [Memory viewer](https://claw-lens.com/monitoring/memory-viewer.md): Browse and read the files in your OpenClaw agent's workspace memory directory. Check context sizes and file contents without leaving the dashboard.
- [Overview](https://claw-lens.com/monitoring/overview.md): The Overview dashboard gives you an at-a-glance view of your entire OpenClaw deployment — costs, sessions, agent health, active models, and recent activity — all on one page.
- [Sessions](https://claw-lens.com/monitoring/sessions.md): The Sessions browser lists every recorded agent session with token counts, costs, errors, and context health, and lets you drill into per-session details including model breakdown, tool usage, and message-level charts.
- [Token Usage](https://claw-lens.com/monitoring/token-usage.md): The Token Usage page gives you a complete picture of how your agents consume tokens and incur costs — broken down by time period, model, agent, and session type, with trend charts and expandable per-agent breakdowns.
- [Quick Start](https://claw-lens.com/quickstart.md): Run Claw Lens in under a minute using npx or a global install, then open the dashboard at http://localhost:4242.
- [CLI reference](https://claw-lens.com/reference/cli.md): Complete reference for the claw-lens command-line interface, including all options and environment variables.
- [Data Storage](https://claw-lens.com/reference/data-storage.md): How Claw Lens stores and handles your agent data — all local, no external calls, no telemetry.
- [FAQ](https://claw-lens.com/reference/faq.md): Answers to common questions about Claw Lens setup, behavior, and data handling.