tokentap - intercept and visualize LLM token traffic
Python proxy that intercepts LLM API traffic and shows real-time token usage, costs, and context window in a terminal dashboard. Useful for debugging prompts and tracking spend.
This entry doesn't have a long-form writeup yet. Follow the source link above for the full context.
Related entries
unclog - find and fix Claude Code context bloat
CLI that scans ~/.claude for MCPs, skills, hooks, and CLAUDE.md files, shows how many tokens each consumes before you type, and lets you remove items with reversible snapshots.
sqz - context compressor for LLM CLIs
Rust CLI that compresses prompt and context payloads before they hit the model, trading a small accuracy delta for measurable token-cost savings.
soft-ue-cli - Claude Code bridge for Unreal Engine
Python CLI plus UE plugin that lets Claude Code spawn actors, edit blueprints, call functions, capture screenshots, and manage PIE sessions in real time. Uses an in-process HTTP bridge to UE5.
kolo - greppable debugger for Python agents
Python debugger built for AI agents: captures every executed function call, return value, local variable, and HTTP request into greppable trace files.