Spotlight by Backplanes: Session analysis tool for Claude Code and Codex agents
By
Nick Vlku
Crispy enough to crunch, soft enough to enjoy. A good bake.
Summary
Spotlight by Backplanes is a tool that reads Claude Code and Codex sessions to provide session reports and analysis. It goes beyond simple session replay by offering an interpretation layer that identifies retry storms, redundant tool loops, repeated lookups that should have been cached, and other engineering insights. Every finding in the report must cite the specific moment in the session it came from. The tool helps developers improve their code by showing what agents actually did and how to get better with each session.
Key quotes
· 3 pulledThe session replay is the easy part; the interpretation layer is the product.
Every finding has to point at the specific moment in the session it came from. If it can't cite the event, it doesn't ship.
It surfaces retry storms, redundant tool loops, repeated lookups that should have been cached.
You might also wanna read
Undocumented Claude Code Features Revealed Through Source Code Analysis
An in-depth technical analysis of the Claude Code source code revealing numerous undocumented configuration features. Key findings include t
Claude Code Checkpoints: Developer Tool for Tracking Code Changes
Claude Code Checkpoints is a companion app for developers using Claude AI that provides automatic change detection, one-click project snapsh
cc-canary: Offline Drift Detection Tool for Claude Code
A pre-alpha drift detection tool for Claude Code, packaged as two Agent Skills. It reads existing JSONL session logs from Claude Code to det
claude-replay: Convert AI Coding Agent Sessions into Interactive HTML Replays
claude-replay is an open-source tool that converts AI coding agent session logs (from Claude Code, Cursor, Codex CLI, Gemini CLI, and OpenCo
Argus: VS Code Extension for Claude Code Session Debugging and Performance Analysis
Argus is a VS Code extension designed to monitor and analyze Claude Code sessions, providing developers with insights into AI-assisted codin
