# cwc-workshops | Anthropic | Knowledge Base | Instagit

GitHub Stars: 1.7k

Repository: https://github.com/anthropics/cwc-workshops

---

## Articles

### [How to Implement Dispatch Handlers for Fanning Out Work to Multiple Sessions](/anthropics/cwc-workshops/how-to-implement-dispatch-handlers-fan-out-work-multiple-sessions)

Learn to implement dispatch handlers in Anthropic CWC workshops. Fan out complex tasks to specialized agents using a central dispatch router from tool names to Python functions.

- Tags: how-to-guide
- Published: 2026-07-21

### [How to Implement Memory Mount for Shared Knowledge in Analyst Sessions](/anthropics/cwc-workshops/how-to-implement-memory-mount-shared-knowledge-analyst-sessions)

Learn to implement memory mount for shared knowledge in analyst sessions by supplying a memory_store resource with read_write access when creating your session.

- Tags: how-to-guide
- Published: 2026-07-21

### [How to Implement Scorecard Validation for Agent Output Quality](/anthropics/cwc-workshops/how-to-implement-scorecard-validation-agent-output-quality)

Implement scorecard validation for agent output quality using the validateScorecard function. Enforce schema compliance and get detailed feedback on validation failures.

- Tags: how-to-guide
- Published: 2026-07-21

### [How to Stream Session Events from Claude Agents in Real-Time](/anthropics/cwc-workshops/how-to-stream-session-events-claude-agents-real-time)

Stream session events from Claude agents in real-time using client.beta.sessions.events.stream(). Handle agent messages, tool calls, and status updates as they happen.

- Tags: how-to-guide
- Published: 2026-07-21

### [How to Create Sub-Agents that Delegate Tasks to Specialist Agents](/anthropics/cwc-workshops/how-to-create-sub-agents-delegate-tasks-specialist-agents)

Learn to create sub agents that delegate tasks to specialist agents using Anthropic API and orchestrator tools. Optimize task delegation for parallelizable and context-heavy workloads.

- Tags: how-to-guide
- Published: 2026-07-21

### [Vault Integration for Secure Credential Handling in Claude Agents: A CWC Workshops Implementation Guide](/anthropics/cwc-workshops/vault-integration-for-secure-credential-handling-in-claude-agents)

Learn how to integrate HashiCorp Vault for secure credential handling in Claude agents. Eliminate hard-coded secrets and leverage built-in secret management with CWC Workshops.

- Tags: how-to-guide
- Published: 2026-07-20

### [Claude Agent Evaluation with Decision Probes: A Technical Guide to the CWC Agent-Battle Harness](/anthropics/cwc-workshops/claude-agent-evaluation-with-decision-probes)

Evaluate Claude Managed Agents with decision probes in the CWC agent-battle harness. This technical guide details using synthetic Minecraft states for rapid, rubric-based scoring.

- Tags: how-to-guide
- Published: 2026-07-20

### [Using Memory Stores for Cross-Session Persistence in Claude Agents](/anthropics/cwc-workshops/using-memory-stores-for-cross-session-persistence-in-claude-agents)

Learn how to use memory stores for cross-session persistence in Claude agents. Mount a CMA Memory Store as a virtual file system for shared, persistent data across chat sessions.

- Tags: deep-dive
- Published: 2026-07-20

### [Workflow for Versioned Agent Updates and Skill Publishing](/anthropics/cwc-workshops/workflow-versioned-agent-updates-skill-publishing)

Learn the workflow for versioned agent updates and skill publishing in the anthropics/cwc-workshops repository. Discover idempotent deployment for Claude Managed Agents.

- Tags: workflow
- Published: 2026-07-18

### [How to Implement Outcome Evaluation with File-Based Rubrics for Grading in CWC Workshops](/anthropics/cwc-workshops/how-to-implement-outcome-evaluation-file-based-rubrics-grading)

Learn how to implement outcome evaluation with file-based rubrics for grading in CWC workshops. Use YAML rubrics and an LLM judge to assess agent responses effectively.

- Tags: tutorial
- Published: 2026-07-18

### [How MCP Servers Connect to Claude Managed Agents: The Vault Credential Pattern Explained](/anthropics/cwc-workshops/how-mcp-servers-connect-managed-agents-vault-credential-pattern)

Learn how MCP servers connect to Claude Managed Agents using the vault credential pattern. Discover how static bearer vault credentials bind relay secrets to server URLs.

- Tags: explanation
- Published: 2026-07-18

### [How the Scorecard Outcome Grading System Works: Programmatic and LLM-as-Judge Evaluation](/anthropics/cwc-workshops/scorecard-outcome-grading-system-programmatic-llm-as-judge-evaluation)

Understand the Scorecard outcome grading system with hybrid evaluation. Learn how programmatic and LLM-as-judge methods assess agent task completion for standardized results.

- Tags: deep-dive
- Published: 2026-07-18

### [Orchestrator Pattern for Handling Agent Event Streams Server-Side: Implementation Guide](/anthropics/cwc-workshops/orchestrator-pattern-handling-agent-event-streams-server-side)

Learn the orchestrator pattern for server-side agent event stream handling. Ingest, parse, route, and consolidate agent tasks for efficient workflow management.

- Tags: how-to-guide
- Published: 2026-07-18

### [How the `provision.ts` Module Creates Sub-Agents with Coordinator Rosters](/anthropics/cwc-workshops/how-provision-ts-module-creates-sub-agents-coordinator-rosters)

Learn how provision.ts creates sub-agents with coordinator rosters by instantiating specialist agents and building a hierarchical multiagent structure for parallel workflow dispatch.

- Tags: internals
- Published: 2026-07-18

### [SKILL.md File Format and Required Frontmatter Structure](/anthropics/cwc-workshops/what-skill-md-file-format-required-frontmatter-structure)

Learn the SKILL.md file format and required `name` and `description` frontmatter for Instagit workshop agents. Understand how to register your skills efficiently.

- Tags: api-reference
- Published: 2026-07-18

### [How to Mount a Memory Store to a Session with Read_Write Access](/anthropics/cwc-workshops/how-to-mount-memory-store-session-read-write-access)

Mount a memory store with read_write access to your session using the Anthropic CLI resource flag. Learn how to configure your session for memory store access.

- Tags: how-to-guide
- Published: 2026-07-18

### [user.message vs user.define_outcome: Event Types in Anthropic Managed Agents](/anthropics/cwc-workshops/difference-between-user-message-user-define-outcome-events)

Understand the difference between user.message and user.define_outcome events in Anthropic Managed Agents. Learn how to trigger responses and enable iteration loops for your agents.

- Tags: deep-dive
- Published: 2026-07-18

### [How to Implement Custom Tool Calls that Require Action and Wait for Server Response in Anthropic's CWC Workshops](/anthropics/cwc-workshops/how-to-implement-custom-tool-calls-require-action-wait-server-response)

Learn to implement custom tool calls in Anthropic's CWC Workshops. Pause execution with requires_action, perform server-side async work, and resume agent sessions.

- Tags: how-to-guide
- Published: 2026-07-18

### [Session Event Log Architecture and Durable Conversation State in Claude Managed Agents](/anthropics/cwc-workshops/session-event-log-architecture-durable-conversation-state)

Understand session event log architecture and durable conversation state in Claude managed agents. Learn how to reconstruct client-side state from immutable server-side events for resilient conversations.

- Tags: architecture
- Published: 2026-07-18

### [How to Create and Publish a Custom Skill for Claude Code: A Complete Guide](/anthropics/cwc-workshops/how-to-create-publish-custom-skill-claude-code)

Learn to create and publish custom Skills for Claude Code using SKILL md files and Python implementations. Follow this guide from the anthropics cwc workshops repository to build reusable code bundles.

- Tags: how-to-guide
- Published: 2026-07-18

### [How Bounded Fan-Out Concurrency Works in analyzeMany](/anthropics/cwc-workshops/how-bounded-fan-out-concurrency-works-analyze-many-function)

Understand how bounded fan-out concurrency in analyzeMany efficiently processes ticker lists using a fixed worker pool and shared counter to manage parallel analysis.

- Tags: how-to-guide
- Published: 2026-07-18

### [Event Stream Pattern Using SSE for Streaming Agent Responses in Anthropics CWC Workshops](/anthropics/cwc-workshops/event-stream-pattern-sse-streaming-agent-responses)

Learn the event stream pattern with SSE for agent responses. Discover how Anthropics CWC workshops use SSE for resilient, reconnected streaming and duplicate event skipping.

- Tags: deep-dive
- Published: 2026-07-18

### [How to Implement `user.custom_tool_result` for Tool Call Responses in Anthropic Managed Agents](/anthropics/cwc-workshops/how-to-implement-user-custom-tool-result-tool-call-responses)

Learn how to implement user.custom_tool_result to send custom tool execution results back to Anthropic managed agents. Follow our guide for seamless integration.

- Tags: how-to-guide
- Published: 2026-07-18

### [How Outcomes Are Graded Using the Scorecard System in Research Desk](/anthropics/cwc-workshops/what-are-outcomes-how-graded-scorecard-system)

Learn how outcomes are graded using the scorecard system in Research Desk. Discover concise task definitions and grading rubrics evaluated by a strict JSON schema validation.

- Tags: how-to-guide
- Published: 2026-07-18

### [How the Dreaming Service Consolidates Past Transcripts into Memory Stores](/anthropics/cwc-workshops/how-dreaming-service-consolidates-transcripts-memory-stores)

Learn how the Dreaming Service consolidates past transcripts to create new memory stores for Claude models. Our batch job feature distills sessions for future agent reference. Read more now.

- Tags: internals
- Published: 2026-07-18

### [Memory Store Architecture in the Agents-That-Remember Workshop: A Technical Deep Dive](/anthropics/cwc-workshops/memory-store-architecture-agents-that-remember-workshop)

Explore the CMA Memory Store architecture in the agents-that-remember workshop. Discover persistent, filesystem-like storage for managed agents enabling cross-session state retention and memory consolidation.

- Tags: deep-dive
- Published: 2026-07-18

### [How Custom Tools Function in the Research-Desk Workshop: A Complete Technical Guide](/anthropics/cwc-workshops/how-do-custom-tools-function-research-desk-workshop)

Discover how custom tools function in the research-desk workshop. Learn about dispatching analysis tasks with custom tools, parallel processing, and result compilation in this technical guide.

- Tags: how-to-guide
- Published: 2026-07-18

### [Skills vs MCP Servers in the Agent-Battle Workshop: Key Differences Explained](/anthropics/cwc-workshops/difference-between-skills-and-mcp-servers-agent-battle-workshop)

Understand the core differences between Skills and MCP servers in the agent-battle workshop. Learn how static Skills contrast with dynamic MCP tool APIs to optimize your agent development.

- Tags: deep-dive
- Published: 2026-07-18

### [How the Multi-Agent Coordinator Roster Works in Claude Managed Agents](/anthropics/cwc-workshops/how-does-multi-agent-coordinator-roster-work-claude-managed-agents)

Understand the multi-agent coordinator roster in Claude Managed Agents. Discover how it maps agent capabilities to endpoints for dynamic request routing. Learn more!

- Tags: deep-dive
- Published: 2026-07-18