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

Claude Code v2.1.302 ·

Agent tool instructions describe forking in more places when forking is on

The Agent tool's instructions to Claude now have separate fork wording and a "When to fork" section, shown only when forking is enabled

Under the hood Internal Changes
JSON All of v2.1.302
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
SubagentsArea: what it touches
Internal ChangesKind: in v2.1.302,
Internal ChangesSection of the release

Unclear What turns the fork version of these instructions on is not shown.

What

The Agent tool lets Claude hand part of a task to a subagent, a helper copy of Claude. A fork is a subagent that starts from the current conversation. The instructions Claude receives about this tool have changed in how fork wording is chosen:

  • The fork wording no longer appears only together with the background-subagent text. Each has its own condition.
  • The background text has a fork version and a non-fork version.
  • When forking is on, the instructions include a "When to fork" section and say: "A fork keeps its tool output out of your context. If you are the fork, execute directly - don't re-delegate."
  • The "When to use" text can be replaced by a value set for each agent.

The stock Agent tool description captured under this release is the same as in the previous capture, so this wording shows up only where forking is enabled.

Why

What Claude is told about forking shapes when it hands work off, and a fork is told to do the work itself rather than hand it on again.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhat turns the fork version of these instructions on is not shown.

See this entry in the whole of v2.1.302 →

Feedback