Sign in
← AI PulseAug 24, 2026

Wire · news · Single-source brief

Claude Code Updates Introduce New Monitoring and Configuration Features

Claude Code has introduced several new features, including enhanced monitoring for loop tasks, expanded model picker customization, and refined prompt caching controls.

By Illumora Editorial

Source · Aug 24, 2026, 11:40 PM · On Illumora · Aug 24, 2026, 11:47 PM

Media from the primary source — shown here so you can stay on Illumora.

Rewritten from one allowlisted primary — not independent enterprise reporting. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →Claude Code What's New + releases — Claude Code changelog - Claude Code Docs
Save

Recent updates to Claude Code introduce new capabilities for monitoring usage, configuring models, and managing prompt caching. These changes aim to provide users with more control and visibility over their interactions within the environment.

Key Points

  • A Loops breakdown has been added to /usage, displaying per-loop run count, total tokens, tokens per run, and last run.
  • The modelPicker setting allows for curating the /model picker with an ordered, labeled list of models, including Vertex and Bedrock IDs.
  • New promptCacheTtl and subagentPromptCacheTtl settings enable a 1-hour prompt cache for the main conversation and 5-minute caches for subagents.
  • The modelPricing managed setting now uses an organization's contracted per-model rates and discount multiplier for /cost, the status line, and telemetry cost figures.
  • A keyless sign-in option under /login via the Anthropic Console has been added for organizations that do not permit API keys.
  • A "Skipped sources" line in /status now lists managed settings sources that are present but not applied due to higher-precedence sources.

Context

According to the Claude Code changelog, these updates provide more granular control and transparency for users. The enhancements address various aspects of the user experience, from monitoring resource consumption to customizing model selection and managing authentication methods.

Why It Matters

These updates offer builders greater control over Claude Code environments, enabling more precise cost tracking, improved operational visibility for automated tasks, and flexible authentication options. This can lead to more efficient resource management and better alignment with organizational policies.

What To Do

  • Review the /usage command to monitor loop task performance and token consumption.
  • Explore the modelPicker setting to customize the available models for your team.
  • Adjust promptCacheTtl and subagentPromptCacheTtl to optimize caching behavior for API key and cloud-provider users.
  • Note the new keyless sign-in option under /login for organizations with API key restrictions.
  • Check the /status output for any skipped managed settings sources.

Keep Exploring

/atlas/claude-family