TokenDam - A linter for LLM token spend — that gates cost in CI

Your agents burn tokens — resending uncached prompts, dragging dead tools, replaying full history. TokenDam is a linter for LLM spend: paste a trace and see the line-item waste, each with a $/month figure and the exact fix (runs in your browser — your trace never leaves the tab). Put it in CI and the GitHub App audits every PR, fails the build on a cost regression, and opens a prompt-cache fix PR. Think ESLint, but for your token bill. Free CLI + web; Pro watches every PR.

Hey PH 👋 I'm an indie dev and I kept watching my own AI agents quietly burn tokens — resending the same uncached system prompt, dragging dead tools around, replaying full history. So I built TokenDam: a linter for LLM token spend. Paste a trace and it shows the line-item waste with a $/month figure and the exact fix — 100% in your browser, nothing uploaded. There's a CLI (npx tokendam), an MCP server, and a GitHub App that audits every PR and even opens a prompt-cache fix PR for you. It's the kind of small, sharp tool I like to ship. Would love your brutal feedback on the report UX and whether the numbers match your real bill. 🙏

TokenDam - A linter for LLM token spend — that gates cost in CI

Replies