Best practices for Claude Code changedbest-practices
Nearest release: v2.1.251, published 13 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+2added
Lines−2removed
From line
394
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits31to this page, all time
The whole hunk
from line 394, old and new numbered
/
from line 394
394394 Delegate research with `"use subagents to investigate X"`. They explore in a separate context, keeping your main conversation clean for implementation.
395395</Tip>
396396
397Since context is your fundamental constraint, subagents are one of the most powerful tools available. When Claude researches a codebase it reads lots of files, all of which consume your context. Subagents run in separate context windows and report back summaries:
397Since context is your fundamental constraint, use subagents to keep research out of it. When Claude researches a codebase it reads lots of files, all of which consume your context. Subagents run in separate context windows and report back summaries:
398398
399399```text wrap theme={null}
400400Use subagents to investigate how our authentication system handles token
from line 501
501501 ```
502502 </Step>
503503
504 <Step title="Test on a few files, then run at scale">
504 <Step title="Test on a few files, then run on all of them">
505505 Refine your prompt based on what goes wrong with the first 2-3 files, then run on the full set. The `--allowedTools` flag restricts what Claude can do, which matters when you're running unattended.
506506 </Step>
507507</Steps>
No line in this hunk matches that.