Argus – VSCode debugger for Claude Code sessions
Analyzes Claude Code sessions, but mostly visualizes what Claude already logs.
A harness framework for building domain-specific agents, the worked finance instance that beats every frontier model on public benchmarks, and the autonomous loop coordinator that drives 100-experiment optimization runs unattended.
150× token inflation finding — you pay to re-read, not generate.
Claude Code users, AI developers tracking LLM costs
LLM cost trackers · Token usage analyzers · Claude dashboard tools
Analyzes Claude Code sessions, but mostly visualizes what Claude already logs.
Yet another coding assessment platform, but this one parses AI agent logs.
Turns your denied Claude Code plans into personalized improvement hooks automatically.
Measures exactly where your coding agent starts failing as context window fills.
Single gist script parsing local JSONL when no official Claude analytics exist.
Local SQLite ledger captures runaway Claude Code sessions before the bill shocks you.