Menu

Post image 1
Post image 2
Post image 3
Post image 4
Post image 5
1 / 5
0

CLAUDE.md Wastes 7K+ Tokens Per Turn; Skills Cut to 50

DEV Community·gentic news·17 days ago
#1y0lRpC9
#ai#tech#opinion#claude#agent#context
Reading 0:00
15s threshold

A 1,000-line CLAUDE.md burns 7,000-10,000 tokens per turn on instructions the model already knows. Skills using progressive disclosure cut that to ~50 tokens. A 1,000-line CLAUDE.md burns 7,000–10,000 tokens per turn in Claude Code. That's instructions the model already knows from reading the codebase, according to a detailed analysis by developer Abd Rahman Saber Abdo. Key facts 1,000-line CLAUDE.md = 7,000-10,000 tokens per turn. Skills load ~50 tokens vs 7K+ for CLAUDE.md. 95% of agent setups don't need a CLAUDE.md. Model at 85% context utilization is measurably worse than at 30%. Recursive skill building: workflow → run → skill → failure → fix. The ritual is everywhere in AI coding agents: you create a CLAUDE.md, list your framework, coding style, and response tone. It feels productive. But it's likely making your agent dumber and wasting money, argues developer Abd Rahman Saber Abdo in a technical deep-dive [According to the source].…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More