Clogmeter is live on Product Hunt: see what your agent instruction files cost

If you use Claude Code, Cursor or Codex, your agent re-reads the same instruction files on every turn: AGENTS.md, CLAUDE.md, Cursor rules, skills. They grow quietly. Rules get copied between files, and sooner or later two of them disagree ("always run the full test suite" in one, "never run slow tests" in another). The model pays for both on every call and starts hedging.

Clogmeter is a small free tool I built to make that visible. Paste or drop your instruction files and it:

• counts the tokens each file and each section costs,
• flags near-duplicate rules across files,
• flags always/never rules that contradict each other,
• suggests what to trim first.

It runs entirely in your browser; nothing is uploaded.

We're live on Product Hunt today, and honest feedback is very welcome, especially on what it misses:
https://www.producthunt.com/products/clogmeter

Try it: https://clogmeter.vercel.app/?ref=producthunt