Guides

Slash Command System Deep Dive: Build Your Own Agent Dispatcher

Build a custom slash command dispatcher in TypeScript using ClaudeClaw as a live working example — bridging simple prompts and real agentic workflows.

$ tar -tzf slash-command-system-deep-dive.tar.gz
  • guide.md — 8-chapter technical guide (~8,000 words): SDK init payload, COMMAND_REGISTRY, resolveCommand(), the dispatcher loop, ClaudeClaw live walkthrough, production hardening, and a hands-on build exercise
  • appendix-a-command-registry-reference.md — Quick-reference card: TypeScript types, resolveCommand() signature, validateRegistry(), design rules, and common routing patterns
  • appendix-b-sdk-init-payload.md — Annotated SDK system / init message with field-by-field explanation and deployment validation pattern
  • checklist-dispatcher-audit.md — 12-item self-audit covering registry integrity, resolution correctness, security, observability, and reliability
  • dispatcher-scaffold.ts — Drop-in TypeScript dispatcher: fully typed, wired to the Claude Agent SDK, reads real agent.yaml via js-yaml with allowedTools enforcement
  • command-registry-example.ts — Minimal working registry with 3 example commands demonstrating routing, aliases, disallowedTools, permissionMode override, and maxTurns override
$29

one-time purchase

Instant download after purchase
📧Download link sent to your email
🔄7-day download access
14-day money-back guarantee
View refund policy

## goes-well-with

From the same shelf

## not-ready-to-buy

Take the field notes instead

One practical write-up a week from the same workbench these kits come from — plus reader pricing when new kits ship.