zwolf25/tokenminning

A context engineering philosophy for maximizing intelligence per token in AI systems.

30Stars on the repository
2Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

doc-convert

01

zwolf25/tokenminning

Skill Claude CodeCodex

Convert documents locally, without spending model tokens — PDF/DOCX/PPTX/XLSX → Markdown, and Markdown → styled DOCX (using a named style preset, e.g. default or report). Local, CloudConvert-style tool; runs as a subprocess, so it costs no model tokens. Use when the user says "convert this to markdown", "pdf to md"…

not rated 30 +3 yesterday A 175 tokens original MIT

visual-diff

02

zwolf25/tokenminning

Skill Claude Code

Run this BEFORE viewing (Read-ing) any screenshot, slide export, or UI mockup image to check whether an AI-made edit worked — not after. This is default behavior, not opt-in: pipe the screenshot through visual-diff.js as part of the same step that produces or locates the image, rather than viewing it first and diffing…

not rated 30 +3 yesterday A 0 tokens original MIT