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.
What it is
A commit to Anthropic's public skills repository, the same collection that includes Claude Agent Skills covered previously, updating the claude-api skill's documentation.
What it does
Adds documentation for an effort field on an agent's model object (agent-configuration only, silently ignored in per-session overrides), an optional version field on agent updates for optimistic concurrency, and an initial_events option on session create that collapses session creation and the first message send into a single call, plus partner pricing and tool-runner corrections.
Why it matters
If you're building on Managed Agents, this skill update is effectively free, always-current API documentation that Claude Code can load on demand instead of you hunting through changelogs to find out what initial_events actually validates.
How to use it
Pull the latest claude-api skill from the skills repo or let Claude Code load it on demand when you're working with Managed Agents sessions.
docx, pptx, xlsx skills patched against path-traversal archives
Anthropic updated its docx, pptx, and xlsx Claude Agent Skills to reject symlink and path-traversal entries during archive extraction and to add template-format support.
Claude Agent Skills: portable capability packages for Claude Code
Claude Agent Skills are portable folders of instructions, scripts, and reference docs that Claude Code loads on demand to gain one specific capability.
Claude Code 2.1.218 Moves /code-review to a Background Subagent
Claude Code 2.1.218 runs /code-review as a background subagent instead of filling the main conversation, and fixes a bug where the left arrow key discarded the conversation with no undo.