Vibe Coding
Tip: tokencut folds recognised tool-output noise and leaves a reference to recover the original
tokencut (created 2026-09-20) is a local CLI and MCP server that wraps a command — `tokencut run -- pytest -v` — and folds known-noisy output while keeping diagnostics, with omitted text retrievable by reference. Its built-in pytest fixture goes from 1,562 tokens to 174 including the recovery notice, an 88.9% cut, and `tokencut demo --json` reproduces it with no model calls; the README is explicit that this is a local tokenizer estimate, not a billing claim. Default filtering preserves unfamiliar output and stronger truncation is opt-in, which is the right default for a tool sitting between an agent and its test suite.
Source
↳ Follow the thread