Communications kit changedcommunications-kit
Nearest release: v2.1.285, published 2 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 29 Sep 2026 19:57 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 29 Sep 2026 20:07 UTC.
Upstream edited
Recorded here
Lines+5added
Lines−5removed
From line
59
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits11to this page, all time
The whole hunk
from line 59, old and new numbered
/
from line 59
5959
6060 Where your code goes: Claude Code runs in your terminal and talks directly
6161 to Anthropic's API, with no third-party servers in the loop. It asks before
62 editing files or running commands. Under our Enterprise agreement, Anthropic
62 editing files or running commands. On our Team or Enterprise plan, Anthropic
6363 does not use your code or prompts to train its models.
6464 Details: https://code.claude.com/docs/en/data-usage
6565 https://code.claude.com/docs/en/security
from line 86
8686 *First thing to try* → run `/init`, then: "the test in [file] is flaky,
8787 figure out why and fix it."
8888
89 🔒 Runs in your terminal, talks only to Anthropic's API. Under our
90 Enterprise plan your code and prompts are not used to train models.
89 🔒 Runs in your terminal, talks only to Anthropic's API. On our Team or
90 Enterprise plan, your code and prompts are not used to train models.
9191 Data usage → https://code.claude.com/docs/en/data-usage
9292
9393 📚 Quickstart · VS Code · Free 1-hr course
from line 464
464464Permission-first by design. Every file edit, shell command, and external
465465call is gated by your approval. The CLI runs in your terminal and talks
466466directly to Anthropic's API, with no third-party servers, and supports
467optional OS-level sandboxing for shell commands. Under our Enterprise plan,
467optional OS-level sandboxing for shell commands. On a Team or Enterprise plan,
468468Anthropic does not use your code or prompts to train its models.
469469
470470*Try it now:* save these two links for the next time the question comes up.
from line 504
504504| - | - |
505505| "Does it work in VS Code?" | Yes. There is a VS Code extension and a JetBrains plugin with the same features, embedded in your editor. [VS Code →](/docs/en/vs-code) |
506506| "Do I have to configure anything first?" | No. Install, then run `claude` in any repo. Run `/init` once and you're set. [Quickstart →](/docs/en/quickstart) |
507| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference, with no third-party servers. Under your Enterprise plan, your code and prompts are not used to train models. [Data usage →](/docs/en/data-usage) |
507| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference, with no third-party servers. On a Team or Enterprise plan, your code and prompts are not used to train models. [Data usage →](/docs/en/data-usage) |
508508| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt; permission prompts gate edits, non-read-only shell commands, and file-tool reads outside that directory. A built-in set of read-only shell commands such as `ls` and `cat` runs without prompting; restrict it with [sandbox `denyRead` rules](/docs/en/sandboxing#filesystem-isolation). [Permissions →](/docs/en/permissions) |
509509| "How is this different from Copilot?" | Copilot autocompletes lines. Claude Code is an agent that reads files, runs commands, and makes multi-file edits. [Overview →](/docs/en/overview) |
510510| "What should I try first?" | A bug you've been putting off because it's tedious. "The test in \[file] is flaky, figure out why." [Quickstart →](/docs/en/quickstart) |
No line in this hunk matches that.