Follow Discord
Sweep 08 Oct 2026 · 18:53Z Build v2.1.295 516 read Stable v2.1.286 Latest v2.1.295 Next v2.1.295 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.292 ·

Subagents can be launched with their own effort level

Launching a subagent can now carry an effort level that overrides the one in the agent's definition, except for forks

You'll notice Improvements
JSON All of v2.1.292
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
SubagentsArea: what it touches
ImprovementsKind: in v2.1.292,
ImprovementsSection of the release

Unclear Whether Claude itself can choose this effort value when calling the Agent tool is not clear.

What

A subagent is a separate helper Claude starts through the Agent tool to work on part of a task. Effort is how much reasoning a model puts in. A subagent launch can now carry an effort value, and when it does, that value replaces the effort set in the agent's own definition. It is also passed along when the subagent runs in its own worktree (a separate working copy of the project). Forked launches, which copy the current conversation, do not take it.

The Agent tool's description, as captured under this release, is unchanged from the previous version.

Why

Each subagent can be given its own reasoning effort when it is started.

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 doubtWhether Claude itself can choose this effort value when calling the Agent tool is not clear.

See this entry in the whole of v2.1.292 →

Feedback