Peter Zhang
Apr 07, 2026 21:04
Claude Code’s new subagent system lets builders parallelize coding duties and run impartial AI critiques. This is when the function really helps.
Anthropic has rolled out detailed steering on subagents inside Claude Code, its AI-powered improvement surroundings. The function lets builders spawn remoted AI cases that deal with analysis, code evaluation, and parallel modifications with out cluttering the principle dialog’s context window.
Consider subagents as disposable specialists. Every one will get its personal context, does a job, and returns solely the outcomes. The principle session stays clear.
When Subagents Really Assist
The framework shines in particular eventualities. Analysis-heavy duties that require studying dozens of recordsdata profit from delegation—a subagent explores and synthesizes somewhat than dumping uncooked content material into the dialog. Unbiased modifications throughout a number of recordsdata can run concurrently, chopping completion time roughly in thirds.
Recent perspective issues too. A subagent reviewing code does not inherit the assumptions from the implementation dialogue. It catches what familiarity obscures.
Anthropic suggests a easy heuristic: if a job requires exploring ten or extra recordsdata, or entails three or extra impartial items of labor, subagents are well worth the overhead.
4 Methods to Invoke Them
Builders can set off subagents by pure language (“Use a subagent to discover how authentication works”), outline reusable customized brokers in markdown recordsdata, set insurance policies in CLAUDE.md that robotically route sure duties, or configure hooks that fireplace on particular occasions like commits.
The customized agent strategy stands out for groups. A safety reviewer outlined as soon as turns into obtainable throughout all periods, robotically catching code touching auth or funds. The configuration lives in .claude/brokers/ and may specify read-only permissions for security.
The place They Do not Match
Subagents aren’t universally higher. Sequential work the place every step depends upon the earlier runs extra cleanly in a single session. Similar-file edits from parallel brokers create conflicts. Fast fixes do not justify the spin-up overhead.
Anthropic additionally warns towards creating too many specialist brokers—it confuses the automated delegation system. A handful of well-scoped choices beats a sprawling roster.
For duties requiring coordination between brokers somewhat than impartial operation, the corporate factors builders towards its separate “agent groups” function, although that carries larger prices.
The steering displays Anthropic’s broader push to make Claude Code viable for complicated enterprise codebases the place context administration turns into the bottleneck.
Picture supply: Shutterstock
