Session Budgets, Geo Pinning, Multiagent Caps: Managed Agents Grows Up
Anthropic's claude-api skill documents an August Managed Agents update adding session and deployment spend budgets, inference geo pinning, and a multiagent shared usage cap.
What it is
An update to Anthropic's official claude-api Claude Agent Skill, mirroring the August 5 Managed Agents feature launch.
What it does
It documents a budget object settable at session or deployment creation (in minor-unit cents), budget_reached pause behavior, a session.usage event, the ability to change or remove a budget to resume a paused session, a shared cap across multiagent setups, and per-session or per-agent inference geo pinning that isn't retroactively grandfathered.
Why it matters
Anyone running Managed Agents in production now has a built-in way to hard-cap spend per session or deployment instead of relying on external monitoring to catch a runaway agent, building on the July Managed Agents update.
How to use it
Pull the updated claude-api skill and set a `budget` object on session or deployment creation if you need a hard spend ceiling on Managed Agents.
always_allow, always_ask, and Now auto: Claude's Managed Agents Grows a Middle Option
Anthropic's claude-api skill documents a new auto permission policy for Managed Agents that runs low-risk tool calls, denies high-risk ones automatically, and pauses for human approval only when the risk is indeterminate.
claude-api Skill Adds a Non-Interactive Prompt-Audit Subcommand
Anthropic's claude-api Claude Agent Skill gained a prompt-audit subcommand that scans a prompt's instructions against dated-pattern tables and outputs a findings report with a proposed diff.
Effort Levels, Session Versioning, and initial_events Land in Claude's API Skill
Anthropic updated the claude-api Claude Agent Skill to document five new Managed Agents features, including a model effort level, optimistic-concurrency versioning, and a combined initial_events call.