Claude Code 2.1.243
By Steven Van ·
Added a Loops breakdown to /usage: per-loop run count, total tokens, tokens per run, and last run, so runaway or chatty /loop tasks are easy to spot Added…
The /usage command in Claude Code 2.1.243 adds a Loops breakdown, showing per-loop run count, total tokens, tokens per run, and last run, so a runaway or chatty /loop task is easier to spot.
- A new modelPicker setting lets teams curate the /model picker with an ordered, labeled list of models, including Vertex and Bedrock ids, either appended to or replacing the built-in lineup.
- New promptCacheTtl and subagentPromptCacheTtl settings let API-key and cloud-provider users keep a 1-hour prompt cache on the main conversation while subagents stay at 5 minutes.
- A modelPricing managed setting lets an organisation's contracted per-model rates and discount multiplier feed into /cost, the status line, and telemetry cost figures instead of list price.
- /login now offers a keyless sign-in option, "Sign in with your Console account", alongside creating an API key, for organisations that don't allow API keys.
- /status gains a Skipped sources line listing managed settings sources, such as managed-settings.json, that are present but not applied because a higher-precedence managed source is active.
- /mcp and /plugins now show a managed marker on claude.ai connectors whose authentication is managed by the organisation.
Full details are in the changelog.
Claude Code
Anthropic's agentic coding tool — Claude in your terminal, IDE, desktop app and browser, reading and editing your codebase, running commands, opening pull requests and working on tasks in the cloud.
View Claude Code →