AIToday
Large Language ModelsAI Coding AssistantsZenn AI/MLPublished: Nov 9, 2026, 06:00 JST

Claude Code startup load trimmed: CLAUDE.md halved from 6.1k to 3.3k chars

Send on LINE
Claude Code startup load trimmed: CLAUDE.md halved from 6.1k to 3.3k chars

3 Key Points

  1. What happened

    An operator running Claude Code via claude -p logged roughly 45,000 characters of instruction files loaded at every launch on 2026-11-07 and cut the automated-run CLAUDE.md from about 6,100 to about 3,300 characters by moving history and test results to separate files.

  2. Why it matters

    Splitting out material that does not need to be re-read on every launch appears to make each automated session start lighter, and counting characters quickly shows which files carry the most weight.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The official Claude Code documentation says one thing; the author does another in their own setup. On the documentation side, the core advice is to write requests down to the target file or function, keep CLAUDE.md under 200 lines, move multi-step procedures into skills whose bodies load only when used, tag rule files with paths so they load only when matching files are touched, match the model and effort level to the task, disable unused MCP servers, and push long outputs to subagents or output-filtering hooks. As context, the official cost page cites an enterprise average of about $13 per developer per working day (monthly $150–250), with 90% of users under $30 a day, while noting this is an API cost benchmark, not a subscription bill or weekly limit number.

The author's own experiment seems to have come from an unattended claude -p setup that could launch up to 10 times an hour. The measurement on 2026-11-07 showed that the instructions loaded at every launch — CLAUDE.md, shared rules, work instructions, the index — totaled about 45,000 characters. Three changes followed: moving history, known issues and test results out of the unattended folder's CLAUDE.md (about 6,100 to about 3,300 characters), rewriting the index about 25% shorter, and instructing later restarts not to re-read rules and the index. The author frames the common thread simply as sorting by whether something must be read every time.

FAQ
How did the author measure where the startup load was coming from?
On 2026-11-07 the author counted the instruction files read at each launch — CLAUDE.md, shared rules, work instructions and the index — and found they totaled about 45,000 characters.
What did the author do to shrink the CLAUDE.md?
History, known issues and test results were moved to separate files, taking the unattended-run CLAUDE.md from about 6,100 to about 3,300 characters, and the index was rewritten about 25% shorter.
Did the author stop reading rules on every restart?
For second and later launches that pick up where a finished run left off, the instructions say not to re-read rules and the index, treating what the first launch read as given.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleAI firms have sold $300 billion of stock in 2026, with $100 billion more on tap