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 steering on managing periods throughout 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 totally.
The corporate’s technical workers member Thariq Shihipar laid out the logic in a weblog submit that reads extra like tribal data than typical documentation. The core downside? Context rot—the place mannequin efficiency degrades as extra tokens pile up and a focus will get unfold skinny throughout irrelevant cruft.
5 Methods to Deal with Context Bloat
Claude Code now provides builders a call tree at each flip:
Proceed works when the whole lot within the window nonetheless issues. /rewind (or double-tap Esc) helps you to leap again to any earlier message and reprompt, dropping the whole lot after that time. Anthropic suggests this beats the intuition to sort “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 concentrate on the auth refactor, drop the take a look at debugging.” The catch? Autocompact fires when context is almost full, exactly when the mannequin performs worst as a consequence 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 subsequent 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 father or mother session.
The Psychological Mannequin
Anthropic’s inside take a look at: “Will I would like this instrument output once more, or simply the conclusion?” If simply the conclusion, spin up a subagent for codebase searches, verification runs, or doc writing.
The steering suggests beginning recent periods for genuinely new duties, despite the fact that 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.
Dangerous autocompacts usually occur when Claude cannot predict the place your work is heading. A protracted debugging session will get summarized, then you definately ask about “that different warning in bar.ts” that received 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 growth periods. Whether or not this strikes the needle on enterprise adoption stays to be seen, however builders burning by context on complicated codebases lastly have documented methods past trial and error.
Picture supply: Shutterstock
