Lawrence Jengar
Apr 16, 2026 00:53
Anthropic releases /utilization command and context administration information for Claude Code, serving to builders navigate 1 million token periods extra successfully.
Anthropic dropped a brand new /utilization command for Claude Code on April 15, alongside detailed steerage on managing periods inside the AI coding assistant’s a million token context window. The replace addresses a rising ache level builders have flagged: determining when to proceed, compact, or nuke a session solely.
The corporate’s technical workers member Thariq Shihipar laid out the logic in a weblog publish that reads extra like tribal data than typical documentation. The core drawback? Context rot—the place mannequin efficiency degrades as extra tokens pile up and a spotlight will get unfold skinny throughout irrelevant cruft.
5 Methods to Deal with Context Bloat
Claude Code now presents builders a choice tree at each flip:
Proceed works when all the pieces within the window nonetheless issues. /rewind (or double-tap Esc) permits you to leap again to any earlier message and reprompt, dropping all the pieces after that time. Anthropic suggests this beats the intuition to kind “that did not work, attempt X as a substitute”—as a substitute, rewind to only after helpful file reads and provides cleaner directions.
/compact asks Claude to summarize the session and exchange historical past with that abstract. It is lossy however automated. You possibly can steer it: “/compact give attention to the auth refactor, drop the take a look at debugging.” The catch? Autocompact fires when context is sort of full, exactly when the mannequin performs worst as a result of context rot.
/clear places you in management. You write what issues and begin recent. Extra work, cleaner slate.
Subagents deal with the messiest situation—when the following chunk of labor will generate tons of intermediate output you will not want once more. Spawning a subagent offers it a recent context window; solely the ultimate report comes again to the mother or father session.
The Psychological Mannequin
Anthropic’s inside take a look at: “Will I would like this software output once more, or simply the conclusion?” If simply the conclusion, spin up a subagent for codebase searches, verification runs, or doc writing.
The steerage suggests beginning recent periods for genuinely new duties, though 1M context technically permits marathon periods. For associated follow-up work—like documenting a characteristic you simply constructed—staying in session avoids costly file rereads.
Unhealthy autocompacts sometimes occur when Claude cannot predict the place your work is heading. An extended debugging session will get summarized, then you definately ask about “that different warning in bar.ts” that bought dropped from the abstract. With the bigger context window, Anthropic recommends proactive /compact with specific route earlier than the automated set off fires.
The replace displays Anthropic’s push to make Claude Code extra sensible for prolonged improvement periods. Whether or not this strikes the needle on enterprise adoption stays to be seen, however builders burning via context on complicated codebases lastly have documented methods past trial and error.
Picture supply: Shutterstock