← toolbox

TokenEcon

v0.2.1

A pacing model for AI usage: balances Claude Pro's 5-hour and weekly windows, plus ChatGPT Codex plans and free OpenRouter and Groq tiers, and tells agents when to speed up, cruise, slow down or pause.

major toolprojectexperiment

At a glance

Status
work in progressActively changing; expect things to move.
Being worked on?
Being worked on
Version
v0.2.1
Shelf
Prototypes and projects
Added
Last updated
Known bugs
None noted
Runs
Here, at /tokenecon
Saves your data
Browser storage (localStorage)

What it does

What's next

What changed

  1. v0.2.1

    My week editor: set how heavy each hour of your day is, plus a weekend factor, so the pace follows your real week.

  2. v0.2.0

    Providers tab: ChatGPT Plus and Pro (Codex), OpenRouter free and Groq free, with a quota calculator, routing across allowances, and the same agent contract and Telltale readings for all of them.

  3. v0.1.1

    Renamed from Pacemaker to TokenEcon; the old address redirects and saved data carries over.

  4. v0.1

    First workbench: engine with three model versions, week simulator with charts, concept agents, calibration Lab and roadmap.

STORAGE — Browser storage (localStorage)

Your typed meter numbers, settings, calibration log and agent choices save automatically in this browser only and are never sent anywhere. Clearing site data, or switching browsers or devices, loses them: use Settings → Download backup to keep a copy, and Restore to bring it back.

Export: JSON download available · Import: supported

The write-up

TokenEcon

Goal

Claude Pro meters you on two clocks at once: a rolling 5-hour session and a weekly limit, and other services (ChatGPT's Codex plans, OpenRouter and Groq free tiers) have allowances of their own. TokenEcon is a workbench for turning those meters into a pacing rule: how fast should automatic agents work right now so the week is spent well, not burned in two days and not left half unused when it resets? It is a mock-up and a model today, built so the rule can later be asked by real agents.

How it works

Saving and privacy

Everything stays in this browser: your typed numbers, settings, calibration log, provider choices and agent choices. Nothing is sent anywhere and nothing reads your Claude account; you copy the numbers in yourself. Use Settings → Download backup to keep a copy. It is a working model, not a promise: Anthropic does not publish how the limits are counted, so every constant is a setting to calibrate.

Current state

Work in progress. The engine, the simulator and the provider calculations are finished and tested; the real numbers (how much of the week one session costs, the shape of your own week, each provider's exact limits and reset hour) wait for calibration. The limits for the other providers are starting values taken from public write-ups as of 2026-11-13, each with its source on the Providers tab, and providers change them without notice.

Changelog