The measured data kit: two scripts and this week's datasets, $39
Everything on this site is produced by two MIT scripts and a set of live connectors. The kit is the scripts, the connectors, the priors and calibration, and every dataset, regenerated weekly for a year from the moment you buy.
What is in the zip
quota_report.py: the session cost anatomy on your own~/.claude/projects, one command, with the replay cap as a flag.demand_sim.py+priors.json+calibration.json+candidates.json: the demand simulator; live connectors for GitHub, npm, VS Code Marketplace, WordPress.org, Hacker News, Apify, MCP registry, Hugging Face Spaces; every prior sourced; calibrated against six real product outcomes.datasets/: the marketplace catalog, the issue gap maps (TSV), the scoring runs with every verdict and its deciding number, and every table on this site as JSON.
Datasets currently on the site
| Dataset | Last pull | Free JSON |
|---|---|---|
| Cost anatomy | 2026-09-23 | JSON |
| Tokens per day | 2026-09-23 | JSON |
| Plugin marketplace | 2026-09-23 | JSON |
| MCP registry | 2026-09-23 | JSON |
| npm MCP servers | 2026-09-23 | JSON |
| Show HN | 2026-09-23 | JSON |
| Issue gap map | 2026-09-23 | JSON |
| Token tools | 2026-09-23 | JSON |
| GitHub trending | 2026-09-24 | JSON |
The JSON is free and stays free. The kit is for people who want the machinery and the weekly rebuild without running it themselves.
The kit: measure your own sessions and the market, weekly
- Session cost anatomy for your own logs (
quota_report.py): the exact report on this site, on your machine, one command; reads only usage fields and lengths. - Demand simulator (
demand_sim.py+ priors + calibration): live connectors for GitHub, npm, VS Code Marketplace, WordPress.org, Hacker News, Apify, MCP registry, Hugging Face; scores what a solo newcomer reached at each attach-point in the last 24 months, calibrated against six real product outcomes before it scores anything. - This week's datasets: every table on this site as JSON and TSV, the plugin marketplace catalog, the issue gap maps, the 50-candidate scoring run with every verdict and its deciding number.
$39, one time. Regenerated weekly for a year; the download link you get keeps serving the newest build. MIT.
Get the kit, $39Card checkout by Stripe on this site's own account; the download page opens the moment payment completes. Questions: riley@agentexchange.work.
Refunds: within 14 days, no questions, riley@agentexchange.work.