CLAUDE.md Best Structure: The Section Order That Holds
A section-by-section layout for CLAUDE.md, derived from three real config files rather than a template, plus the length ceilings that keep each rule findable.
Aug 3011 min read
CATEGORY · 65 ARTICLES
AI Coding Assistants
Articles
AI Coding Assistants
Claude Code /compact Command: What It Cleans and What It Keeps
How Claude Code compaction works under the hood, before-and-after token measurements, prompt caching dynamics, and when to use /compact vs /clear.
Aug 2911 min read
Claude Code Memory Usage: RAM Footprint vs Context Window
Local Node.js process RSS vs remote LLM context memory, V8 heap benchmarks, child process spikes, and how to optimize Claude Code on RAM-constrained machines.
Aug 2911 min read
CLAUDE.md Character Limit: Real Ceilings and the 150k Myth
Does CLAUDE.md have a hard character or token limit? We debunk the 150k limit myth, test instruction compliance degradation, and show how to modularize large rule sets.
Aug 2911 min read
Claude Code Context Window Management: Nothing Empties It
The median turn fills 96% of a 200k window and 46.9% exceed one outright. Context came back down exactly zero times in 89 sessions.
Aug 2812 min read
Claude Code High Token Usage: Where the Bill Comes From
Across 20,285 billed turns the operator typed 47,296 tokens and the input side came to 4.25 billion. Shorter prompts move a rounding error.
Aug 2818 min read
Claude Code Slow After Update: We Measured 17 Versions
Every assistant turn stamps its own version and its own token count, so the question is answerable retroactively. Across 17 versions the cost per turn fell 47% from its peak.
Aug 2712 min read
What Model Does Claude Code Use? Measured, Not Documented
Ten --model values, one billed turn each. One alias bills as a different family, one resolves a version behind its own help text, and the default is not the alias.
Aug 1515 min read