Building autonomous AI agents with the Agent SDK
The Agent SDK quickstart and configuration guides provide steps to set up a project and programmatically control agent tools, permissions, and output.
All sources
code.claude.com
https://code.claude.comcode.claude.com Documentation for AI Agents & MCP
Explore code.claude.com documentation for developing and configuring AI agents using the Agent SDK, managing plugins, and integrating with external systems via MCP and plugins. This resource also covers automated code review, cost management, and customizing self-hosted environments for agent operations.
- Pages
- 210
- 4,363
- Tokens
- ~2.1M
- Updated
- Sep 30, 2026
- Monitoring
- Active
Works with
- ChatGPT
- Claude
- Cursor
- MCP clients
Solutions
What AI Agents Can Do With This Source
Use code.claude.com Documentation to complete source-specific tasks, make informed decisions, and follow evidence-backed workflows.
Understanding Claude Code agent behavior
Documentation on the agent loop explains the message lifecycle, tool execution, and architecture, which is crucial for building, debugging, and optimizing agents.
Developing and managing Claude Code plugins
The plugin documentation provides guidance on creating, adding components to, and managing plugins, including CLI commands and marketplace interactions.
Integrating external tools with Claude Code
Documentation on MCP and channels explains how to connect to external tools and push events into running Claude Code sessions for enhanced workflows.
Automating code reviews for pull requests
The Code Review documentation details how to set up automated PR reviews that use multi-agent analysis to identify logic errors, security vulnerabilities, and regressions.
Optimizing Claude Code operational costs
The cost management guide provides strategies for tracking token usage, setting spend limits, and reducing costs through context management and model selection.
Coverage
What's Indexed from code.claude.com
A quick look at the main areas Bulkgrid has indexed and keeps ready for AI search, MCP, extraction, and change detection.
Agent SDK
/docs/en/agent-sdk
32 pages
Documents core capabilities of the Agent SDK, explaining how to embed Claude Code's autonomous agent loop, configure sessions, and integrate features like custom tools and hooks.
Whats New
/docs/en/whats-new
24 pages
Provides weekly updates on new features and improvements, including advancements in agent permissions, CLI capabilities, cloud planning, and integration tools.
Plugins
/docs/en/plugins
20 pages
Guides users through creating, installing, managing, and distributing plugins, including details on Anthropic's marketplaces and CLI commands for plugin interaction.
Advantages
Why Use Bulkgrid for AI-Ready Sources
Bulkgrid turns important websites into fresh, queryable, AI-ready sources without making teams maintain the infrastructure.
Spend Fewer Tokens
Retrieve the right source context instead of sending large pages, pasted docs, or noisy search results into every prompt.
Improve Answer Accuracy
Ground responses in current, source-backed evidence to reduce hallucinations and avoid relying on stale model memory.
Use Fresh Source Data
Keep important websites automatically recrawled and updated so AI is not working from old content.
Query Instantly
Search already-indexed source content immediately instead of crawling pages at question time.
No Infrastructure Maintenance
Bulkgrid handles crawling, rendering, retries, storage, indexing, recrawls, and change detection.
Change Detection
See when pages are added, removed, updated, or fail so teams can react without checking manually.
Give Your Agents Up-to-Date Knowledge from code.claude.com
Search and use knowledge from code.claude.com in ChatGPT, Claude, Cursor, and any MCP-compatible client.