Skip to content
Kamil BancBook a session

Claims Library Entry

12 Claude Code updates that shipped this week and what each one does

Anthropic shipped 12 significant updates to Claude Code in a matter of days, including scheduled tasks, voice mode, structured auto memory, and multi-agent code reviews. This article breaks down each update, explains what it does, and offers guidance on which ones to prioritize based on your workflow.

Published March 13, 2026 by Kamil Banc

AI ToolsImplementation

Lead claim

Anthropic shipped 12 structural Claude Code updates in days, from scheduled tasks to multi-agent code review.

Atomic Claims

What this article supports

Claim 1 · Source summary

Dismissible /btw Answers

The /btw command answers questions in a dismissible overlay without polluting conversation history.

Claim 2 · Source summary

Scheduled /loop Prompts

The /loop command runs prompts on recurring schedules that expire after 72 hours.

Claim 3 · Source summary

Structured Auto Memory

Claude Code's auto memory now uses a structured three-part format for better cross-session recall.

Claim 4 · Source summary

Multi-Agent Code Review

Multi-agent code review scans entire codebases for bugs and costs approximately $15 to $25 per run.

Claim 5 · Kamil's interpretation

Priority for Daily Coders

Starting with /btw and /loop is the recommended priority for developers who write code daily.

Evidence

Context behind the claims

Quote

"Not incremental patches. Structural changes to how the tool thinks, remembers, schedules, and reviews your work."

Key statistics

72 hours

Maximum lifetime of any /loop scheduled task before it automatically expires

$15 to $25

Approximate cost per run of the multi-agent code review feature, limited to Team and Enterprise subscribers

12 updates

Number of meaningful Claude Code updates Anthropic shipped within the span of days

4 effort levels

Every session now prompts users to choose low, medium, high, or max reasoning effort

Supporting context

The article is a practitioner-authored changelog walkthrough by Kamil Banc, cataloging twelve Claude Code updates shipped within days and explaining the practical workflow impact of each. Claims are drawn directly from the author's descriptions of the new features, including command syntax examples, guardrails like the 72-hour task expiry, and pricing details for the multi-agent review system. The author closes with role-based prioritization guidance, mapping each update to daily coders, report builders, team managers, and API developers. Readers evaluating these claims should note the piece is promotional-adjacent commentary rather than independent benchmarking, and no external primary sources were supplied to verify the feature behavior. Practitioners can apply the findings by testing two updates, such as /btw and /loop, in real sessions to assess fit.

How to Cite

Use the claim-level citation when you need a precise statement. Use the article or claims-collection citation when you want the wider argument and source context.

Recommended

Individual Claim

Best when you need to cite one atomic claim directly inside a memo, deck, research note, or AI output.

"[claim text]" (Banc, Kamil, 2026, https://kbanc.com/claims-library/12-claude-code-updates-that-shipped-this-week-and-what-each-one-does)
Full Context

Original Article

Use this when you want to cite the full newsletter article at AI Adopters Club rather than the structured claims page.

Banc, Kamil (2026, March 13, 2026). 12 Claude Code updates that shipped this week and what each one does. AI Adopters Club. https://aiadopters.club/p/12-claude-code-updates-that-shipped
Research

Claims Collection

Use this when you want to reference the full structured claims collection on this page.

Banc, Kamil (2026). 12 Claude Code updates that shipped this week and what each one does [Structured Claims]. Retrieved from https://kbanc.com/claims-library/12-claude-code-updates-that-shipped-this-week-and-what-each-one-does

Attribution Requirements

  • Include the author name: Kamil Banc.
  • Include the source: AI Adopters Club or the structured claims page.
  • Link to the original article or the claims page you used.
  • Indicate any edits or transformations if you changed the wording.

Related Reading

More from the library