{
  "slug": "12-claude-code-updates-that-shipped-this-week-and-what-each-one-does",
  "title": "12 Claude Code updates that shipped this week and what each one does",
  "date": "2026-03-13",
  "featuredClaim": "Anthropic shipped 12 structural Claude Code updates in days, from scheduled tasks to multi-agent code review.",
  "description": "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.",
  "keyPoints": [
    "New /btw and /loop commands enable quick side questions without polluting context and recurring scheduled prompts within a session",
    "Desktop scheduled tasks persist beyond terminal sessions and can send output to Telegram for mobile team alerts",
    "Auto memory now uses a structured three-part format for better cross-session recall, and voice mode is available to all users",
    "Multi-agent code review scans entire codebases for bugs (costing $15-25 per run) and is available for Team and Enterprise subscribers"
  ],
  "topics": [
    {
      "id": "tools",
      "slug": "ai-tools",
      "label": "AI Tools",
      "description": "Practical tools and platforms for AI implementation"
    },
    {
      "id": "implementation",
      "slug": "ai-implementation",
      "label": "Implementation",
      "description": "Hands-on implementation techniques and frameworks"
    }
  ],
  "claims": [
    "The /btw command answers questions in a dismissible overlay without polluting conversation history.",
    "The /loop command runs prompts on recurring schedules that expire after 72 hours.",
    "Claude Code's auto memory now uses a structured three-part format for better cross-session recall.",
    "Multi-agent code review scans entire codebases for bugs and costs approximately $15 to $25 per run.",
    "Starting with /btw and /loop is the recommended priority for developers who write code daily."
  ],
  "claimTitles": [
    "Dismissible /btw Answers",
    "Scheduled /loop Prompts",
    "Structured Auto Memory",
    "Multi-Agent Code Review",
    "Priority for Daily Coders"
  ],
  "originalUrl": "https://aiadopters.club/p/12-claude-code-updates-that-shipped",
  "claimProvenance": [
    "source-summary",
    "source-summary",
    "source-summary",
    "source-summary",
    "author-interpretation"
  ],
  "quote": "Not incremental patches. Structural changes to how the tool thinks, remembers, schedules, and reviews your work.",
  "keyStatistics": [
    {
      "stat": "72 hours",
      "context": "Maximum lifetime of any /loop scheduled task before it automatically expires"
    },
    {
      "stat": "$15 to $25",
      "context": "Approximate cost per run of the multi-agent code review feature, limited to Team and Enterprise subscribers"
    },
    {
      "stat": "12 updates",
      "context": "Number of meaningful Claude Code updates Anthropic shipped within the span of days"
    },
    {
      "stat": "4 effort levels",
      "context": "Every session now prompts users to choose low, medium, high, or max reasoning effort"
    }
  ],
  "supportingContext": "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.",
  "canonicalUrl": "https://kbanc.com/claims-library/12-claude-code-updates-that-shipped-this-week-and-what-each-one-does",
  "markdownUrl": "https://kbanc.com/md/claims-library/12-claude-code-updates-that-shipped-this-week-and-what-each-one-does.md",
  "jsonUrl": "https://kbanc.com/api/claims/12-claude-code-updates-that-shipped-this-week-and-what-each-one-does.json",
  "source": {
    "publisher": "AI Adopters Club",
    "title": "12 Claude Code updates that shipped this week and what each one does",
    "url": "https://aiadopters.club/p/12-claude-code-updates-that-shipped"
  }
}