AgentScout / Tasks / Writing code / Token usage and cost tracking

Token usage and cost tracking tools for coding agents

Trackers for token usage and spend across coding agents. Of the 338 tools on our writing code page, 8 fit this narrower job. By pricing: 6 open source, 1 source-available, 1 paid, usage-based or enterprise. The most-starred open repos here are Trail Code (10,211 stars), Mission Control (6,358 stars), Tokscale (5,695 stars). Most come from the coding (5), MCP & infra (2), business agents (1) categories.

Updated

GitHub repos (7)

RepoGitHub starsLicenceLast push
Trail Code ↗10,211MIT2026-10-19
Mission Control ↗6,358MIT2026-09-22
Tokscale ↗5,695MIT2026-10-19
abtop ↗3,752MIT2026-09-14
jCodeMunch MCP ↗2,776jCodeMunch-MCP Dual-Use License (free for non-commercial use)2026-10-19
Jevgrep ↗2,675MIT2026-10-19
HiRoute ↗278——

7 repos. Stars and licence come from each repo, checked when the listing was last verified.

FAQ

What are the best AI tools for writing code focused on token usage and cost tracking?

We list 8. The first three by GitHub stars and featured status are Trail Code: Context layer that makes Claude Code, Cursor, Codex and other coding agents faster and cheaper on large codebases.; Mission Control: Self-hosted control plane for dispatching tasks to agents, reviewing runs and tracking spend.; Tokscale: Tracks token usage across AI coding agents from your terminal.

Are there free or open-source options?

Yes: 6 open source, 1 source-available, 1 paid, usage-based or enterprise. Pricing is as each maker states it.

More from writing code

Tools are grouped by what each says it does. Missing one? Submit it free.

Get the best new AI agents, weekly

One short email with new tools, launches and what's worth trying. Free, unsubscribe anytime.