Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.312entry #5

Claude Code v2.1.312 ·

Startup tips can now take their text from a content-link table

Several startup tips, including the /memory tip, now read their text through a content-link table, and the Claude Design tip sits behind a flag

Group of 2 Nothing to try yet Internal Changes
JSON All of v2.1.312
Nothing to try yetTier: how much it should matter to you
3Useful: my rating, 1 to 5
4Signal: worth watching, 1 to 5
TipsArea: what it touches
Internal ChangesKind: in v2.1.312,
What probably matters to youSection of the release

What

Tips are the short hints Claude Code shows, for example at startup. Several tips no longer use a fixed string and instead go through a helper that reads a content-link table, which can replace the default wording.

  • /memory tip: its default text is still "Use /memory to view and manage Claude memory", but it can now be overridden.
  • install-github-app, install-slack-app and code-review-low-fast tips: their text is wrapped the same way.
  • Invalid table: Claude Code logs "Ignoring an invalid content link for tip" and records that the table was rejected.
  • claude-design-contextual tip: shown only when the tengu_cedar_plume flag is true, and the flag's fallback in the code is false.

The flag server returned off for tengu_cedar_plume for this site's account and for the anonymous baseline. No reading has been taken under this release yet.

Why

Tip wording no longer has to stay fixed in the program and may differ from what you saw before. If a table entry is invalid, the default wording is used. The Claude Design tip stays hidden unless the flag is turned on.

Read from
Names in the bundle/memory
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on claude-in-amazon-bedrock touched a line naming /memory after this was published. * [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Browser use tool](https://platform.claude.com/docs/e… build-with-claude/claude-in-amazon-bedrock see the edit
Confirmed since Anthropic's documentation has since written up /memory, on overview. | [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool) | Lets Claude store and read information across conversations in a directory of memory files. | build-with-claude/overview see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up /memory, on overview.

See this entry in the whole of v2.1.312 →

Feedback