Follow Discord
Sweep 03 Nov 2026 · 22:27Z Build v2.1.318 536 read Stable v2.1.311 Latest v2.1.318 Next v2.1.318 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · claude-docs

Good habits for working with Claude Tag changedclaude-tag/users/good-habits

Nearest release: v2.1.318, published 3 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Upstream edited this page at 4 Nov 2026 01:12 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 4 Nov 2026 01:37 UTC.

Upstream edited
Recorded here
Lines+3added
Lines−3removed
From line 17 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits25to this page, all time

The whole hunk

from line 17, old and new numbered
/
lines
from line 17
1717* **Work in public.** Assume everyone in the channel can read the thread, including its checklist and results. Anything your team writes down, like decisions, conventions, and postmortems, is context Claude can use. Knowledge that lives in DMs or was only said aloud is invisible to it. Put anything personal in a DM instead.
1818* **Share control.** Replying in a thread someone else started is how work moves. Redirect the approach, add what the requester didn't know, or pick up the result and run with it.
1919* **Grant broad access.** A channel with more connections (the tools an admin linked for this channel, like GitHub or Drive) produces more useful results, because Claude can join more sources together. The connections are scoped to the agent's identity, so granting them to a channel does not expose anyone's personal data.
20* **Give Claude the destination, not the route.** State the outcome you want and let Claude work out the steps; the [definition of done](#give-every-task-a-definition-of-done) below makes that concrete.
21* **Tolerate the mess.** A first draft posted in the thread is more useful than a polished one in a DM. The thread is the workspace, not the deliverable.
20* **Name the outcome.** Say what you want done and let Claude work out the steps. Give the task a [definition of done](#give-every-task-a-definition-of-done).
21* **Tolerate the mess.** A first draft posted in the thread is more useful than a polished one in a DM.
2222 
2323### Mentioning people who aren't in the channel
2424 
from line 76
7676* **The condition must be observable by Claude.** "Done when CI is green" requires access to CI. If the proof lives in a system the channel isn't connected to, change the condition to one you close yourself.
7777* **Spell out everything the condition includes.** "Babysit this PR until it merges" can produce a merge the moment approvals arrive, before open review comments are addressed. If the full condition is approvals present, comments resolved, and your final go-ahead, write all three into the task.
7878 
79For tasks Claude closes itself, ask it to attach proof, such as the source link, the chart, the test output, or the diff. You read the proof, not the transcript.
79For tasks Claude closes itself, ask it to attach proof, such as the source link, the chart, the test output, or the diff. With that proof, you can confirm the work without going through every step Claude took.
8080 
8181For long-running work, make getting the deliverable somewhere durable part of the definition. Post the file to the thread, push the branch, or open the draft pull request as it goes. See [what survives between replies](https://claude.com/docs/claude-tag/concepts/how-it-works.md#what-survives-between-replies).
8282 
Feedback