Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.308 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · claude-code

How Claude Code works changedhow-claude-code-works

Nearest release: v2.1.240, published 3 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+1added
Lines−35removed
From line 163 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits19to this page, all time

### Be specific upfront ### Give Claude something to verify against ### Explore before implementing

The whole hunk

from line 163, old and new numbered
/
lines
from line 163
163163 
164164## Work effectively with Claude Code
165165 
166These tips help you get better results from Claude Code.
166These tips help you get better results from Claude Code. For more on specific prompts, verification, and planning, see [Best practices](/docs/en/best-practices).
167167 
168168### Ask Claude Code for help
169169 
from line 198
198198 
199199* **Press `Esc`** to stop Claude immediately. The running tool call is canceled and Claude waits for your next instruction. If you have messages queued, Claude Code [sends them next](/docs/en/interactive-mode#queue-messages-while-claude-works).
200200* **Type a correction and press `Enter`** to send it without stopping the running tool. Claude reads it as soon as the current action completes and adjusts before deciding its next step.
201 
202### Be specific upfront
203 
204The more precise your initial prompt, the fewer corrections you'll need. Reference specific files, mention constraints, and point to example patterns.
205 
206```text theme={null}
207The checkout flow is broken for users with expired cards.
208Check src/payments/ for the issue, especially token refresh.
209Write a failing test first, then fix it.
210```
211 
212Vague prompts work, but you'll spend more time steering. Specific prompts like the one above often succeed on the first attempt.
213 
214### Give Claude something to verify against
215 
216Claude performs better when it can check its own work. Include test cases, paste screenshots of expected UI, or define the output you want.
217 
218```text theme={null}
219Implement validateEmail. Test cases: '[email protected]' → true,
220'invalid' → false, '[email protected]' → false. Run the tests after.
221```
222 
223For visual work, paste a screenshot of the design and ask Claude to compare its implementation against it.
224 
225### Explore before implementing
226 
227For complex problems, separate research from coding. Press `Shift+Tab` until the status bar shows `⏸ plan mode on`, then ask Claude to analyze the codebase first:
228 
229```text theme={null}
230Read src/auth/ and understand how we handle sessions.
231Then create a plan for adding OAuth support.
232```
233 
234Review the plan, refine it through conversation, then let Claude implement. This two-phase approach produces better results than jumping straight to code.
235201 
236202### Delegate, don't dictate
237203 
Feedback