Markdown Conversion for Token Reduction

The practice of converting source documents to plain markdown before feeding them to Claude, exploiting the tokeniser's efficiency on clean text versus format-heavy file types.

Reduction ratios

Format Token reduction
HTML → markdown ~90%
PDF → markdown 65–70%
DOCX → markdown ~33%

A 40-page PDF can occupy the same token space as a 130-page markdown file. [src-011]

Key points

  • PDFs and HTML carry layout metadata, CSS, and formatting noise the model does not need for most tasks — only the text content matters [src-011]
  • Recommended conversion tool: Dockling (and similar converters) for fast automated conversion [src-011]
  • Exception: OCR and vision tasks require the original file format [src-011]
  • Pairs naturally with Claude Code Memory best practices: CLAUDE.md should route to separate files rather than inlining all context [src-011]

Related concepts

  • Context Rot — high-format documents accelerate context rot when ingested raw
  • Token Economics — document format is a significant token cost lever
  • Context Management — pre-processing documents is a standard context hygiene step

Source references

  • [src-011] Nate Herk — Claude Code power features cluster (2026-04-20 to 2026-04-27)

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 500 indexed pages and articles.

  1. Wiki concept Session Chaining The practice of decomposing a large project into a sequence of specialised Claude Code sessions — discovery, planning, execution — where each session's output Related by 011
  2. Wiki concept Context Rot The progressive degradation of Claude Code's output quality as session length grows, caused by attention dilution across an ever-larger token history. Related by 011
  3. Wiki concept Session Handoff The practice of packaging the useful state from a Claude Code session into a concise handoff document before clearing context or moving work into Related by 011