Radar / AI coding tools / Tokendoctor
Tokendoctor: the same Claude Code for up to 38% less, audited on your own machine
An MIT-licensed Claude Code plugin that replays your own sessions to show where tokens are overpaid, then proposes settings fixes as diffs you approve — all running locally.
Why it matters
It shows your savings before changing anything: a per-session replay estimates what a smaller context window would have saved, and the author reports 38% lower main-thread cost over six weeks of their own use.
What you could build with it
A solo developer on a Claude Code subscription could run the plugin's session replay to find which of their projects burns the most tokens, then apply the approved window and effort fixes to stretch the monthly allowance further.
Does it hold up?
Usable now and low-risk: it runs locally, changes nothing without an approved diff, and the README is explicit that smaller windows only help sessions that actually pass 400K tokens.
Built with Tokendoctor
- Tokendoctor listed on EveryDev with full audit detailseverydev · Tool listing confirming the MIT license, local-only operation, and the 38% figure with its caveats: no savings if sessions rarely pass 400K tokens.
Learn more
First spotted on github: source.
More AI coding tools
Chrome DevTools MCP: give your coding agent a real browserOfficial MCP server from the Chrome team that lets coding agents drive a live Chrome — console, network, traces…coding · JEV 0.82Orca: the agent development environment for running coding-agent fleetsStably AI's open-source desktop app for running many CLI coding agents side by side — Claude Code, Codex, Cursor and…coding · JEV 0.78Open Code Review: Alibaba's hybrid AI code reviewer, now past 50,000 starsAlibaba's open-source code review CLI (Apache 2.0) pairs deterministic rules with an LLM agent to review git diffs…coding · JEV 0.77Astryx: Meta's agent-ready design system, open sourceMeta open-sourced the React 19 + StyleX design system behind 13,000 internal apps: 150+ accessible components, themes…coding · JEV 0.76GitHub Spec Kit — spec-driven development for coding agentsGitHub's open-source toolkit that gives any coding agent a structured spec, plan, tasks, implement workflow, so specs…coding · JEV 0.75shadcn/improve: audit with your best model, execute with your cheapestAn MIT-licensed Agent Skill that audits any codebase across nine categories with parallel subagents, vets its own…coding · JEV 0.75
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.