Browse the directory

Microsoft open-source course for learning AI agents with lessons on agentic frameworks, design patterns, tool use, agentic RAG, trustworthy agents, planning, multi-agent systems, MCP/A2A/NLWeb, memory, browser use, and Microsoft Agent Framework.

Microsoft open-source Model Context Protocol curriculum with hands-on MCP server, client, security, transport, auth, deployment, Azure, VS Code, Inspector, PostgreSQL, and cross-language examples.

Use Claude Code agent view (claude agents) to dispatch, monitor, peek, attach, and organize many background sessions from one terminal with state icons, PR labels, filters, and shell commands for fleet-style multitasking.

Set up Claude Code GitHub Actions for pull request review: install the Claude GitHub app, store ANTHROPIC_API_KEY in secrets, pin anthropics/claude-code-action to an audited commit SHA with least-privilege permissions, and follow documented security practices.

Set up Claude Code in GitLab CI/CD with maintainer-approved prompts, least-privilege tool access, and Bedrock or Vertex OIDC alternatives from official GitLab integration docs.

Set up Claude Code on Google Vertex AI using official documentation: provider configuration, authentication, project routing, and troubleshooting third-party provider limitations for features like fast mode and computer use.

Use Claude Code slash commands for maintainer workflows: project commands in .claude/commands, namespacing, permission-safe defaults, review before merge, and documenting command scope for contributors.

Delegate repository maintenance to Claude Code subagents: docs drift scans, dependency report triage, README sync checks, and stale issue grooming with scoped tools, read-first policies, and human merge gates.

Roll out the Claude Code VS Code extension to engineering teams: install requirements, sign-in flow, permission modes, shared MCP and hooks access, and managed defaults using official VS Code extension documentation.

Reduce Claude Code context pressure from MCP tools using MAX_MCP_OUTPUT_TOKENS, anthropic/maxResultSizeChars annotations, tool search deferral, alwaysLoad discipline, and pagination patterns from official MCP documentation.

Decide when Claude Code fast mode (/fast) is worth the higher Opus per-token cost: toggle steps, pricing tradeoffs, rate-limit fallback, admin controls, and workflows where standard mode is safer.

Isolate Claude Agent SDK tenants in shared containers using documented options: per-tenant cwd, settingSources disabled, CLAUDE_CONFIG_DIR, CLAUDE_CODE_DISABLE_AUTO_MEMORY, and per-tenant egress rules from official hosting documentation.

Implement OAuth patterns for MCP servers in Claude Code: Dynamic Client Registration, pre-configured client IDs, oauth.scopes pins, authServerMetadataUrl overrides, and keychain token storage from official MCP documentation.

Verify MCP server package provenance before Claude Code installation: registry publisher match, repository ownership, release artifact checksums, maintainer history, and rollback when supply-chain signals fail review.

Pin MCP server package versions before adding them to Claude Code: registry verification, lockfile discipline, npx package pins, supply-chain review, and rollback steps aligned to MCP quickstart and registry documentation.

Defend tool-connected agents against prompt injection using documented Claude Code security practices: MCP trust verification, approval gates, least-privilege tools, untrusted content handling, and human review before side-effect tool calls.

Use Claude Code routines for recurring maintenance: schedule triggers, API and GitHub events, scoped connectors, and review of autonomous cloud runs for backlog grooming, docs drift, and deploy verification.

Use Claude Code Desktop scheduled tasks to run recurring local maintenance: create tasks in Desktop, scope repositories and environments, review autonomous runs, and disable tasks when behavior drifts.

A practical guide for handling secrets when connecting MCP servers and authoring Agent SDK tools in Claude Code: env expansion in .mcp.json, OAuth scope pins, keychain storage, local scope, and redaction before tool arguments reach the model.

Secure Claude Code hooks in shared repositories: version-control hook configs, code review for PreToolUse and PostToolUse scripts, least-privilege matchers, secret scanning, and rollback when hook behavior changes.

A maintainer guide for securing agentic coding workflows in open-source repositories: version-controlled MCP configs, permission defaults, contributor PR review for AI-generated changes, hooks, sandbox boundaries, and public disclosure hygiene.

Install and use the official Claude Code security-guidance plugin before merge: per-edit pattern warnings, end-of-turn and commit git-diff review, and team rollout for command injection, XSS, eval, and dangerous file edits.

Roll out Claude Code server-managed settings for Teams and Enterprise: configure JSON in Claude.ai Admin Settings, understand delivery and caching, verify with /permissions, and use forceRemoteSettingsRefresh when fail-closed startup is required.

Configure Claude Code statuslines for workflow visibility: model identity, context usage, git branch, session mode, and custom metrics so maintainers see agent state at a glance without leaving the terminal.

Configure Claude Agent SDK and Claude Code tool search so large MCP catalogs defer schemas until needed, using ENABLE_TOOL_SEARCH modes, alwaysLoad discipline, and context budgeting from official tool-search documentation.

Troubleshoot Claude Code high CPU, memory pressure, and search misses using official commands: /compact, /context, /heapdump, ripgrep setup, safe mode, and subagent delegation from the troubleshooting documentation.

Plan complex changes with Claude Code ultraplan: launch /ultraplan from the CLI, review cloud drafts on claude.ai, comment inline, and choose web or terminal execution.

Run Claude Code ultrareview with /code-review ultra for multi-agent cloud review, verified findings, PR mode, and optional claude ultrareview CI subcommand.

Run parallel Claude Code Desktop sessions safely: separate windows or tabs per workstream, branch ownership rules, notification hygiene, and handoffs between foreground and background jobs.

Use Claude Code on the web to plan repository changes remotely: connect a repo, run plan-mode sessions in the browser, capture session URLs, and hand plans to local Claude Code for implementation.