Session timeline
Replay any session turn by turn — every tool call, error, and stop reason, with time spent per phase.
Observability for AI agents
Cost, performance, and quality for every Claude Code session, in one view. Built into the workflow you already use.
No credit card required

Move your cursor over it to pull back the coat.
Under the coat
Replay any session turn by turn — every tool call, error, and stop reason, with time spent per phase.
Real cost per session and per agent, priced from live model rates with cache reads and writes counted.
Trace the full spawn tree a session launches — model, tool count, cost, and latency for every subagent.
Tag sessions and record eval scores through the API to track agent quality over time.
See which skills your agents reach for, and how often, across every session.
Share dashboards, manage API keys, and control who sees what.
For the engineer building agents
For the leader paying for them
Wire up your first session
> /plugin marketplace add pando-codes/pando-plugins > /plugin install trenchcoat@pando-plugins # add your key to ~/.claude/settings.json > /trenchcoat:connect
The agents don’t know they’re being watched. We think they’d be proud.
Coming soon
Trenchcoat is expanding beyond Claude Code.
Instrument agents built on the OpenAI Agents SDK and stream their telemetry into Trenchcoat.
A Copilot Extension that reports agent activity from your GitHub workflow into Trenchcoat.
Connect the Trenchcoat plugin and events start flowing from your next session.