By itamarzand88
Professional TypeScript Claude Agent SDK development toolkit — patterns, hooks, control, and architecture
npx claudepluginhub itamarzand88/claude-code-agentic-engineering --plugin agent-sdk-proYou are adding a new TypeScript hook to an Agent SDK project. Use the sdk-hooks-development skill.
Diagnose issues with a TypeScript Agent SDK project — checks SDK installation, TypeScript config, hook implementations, common runtime errors, and provides targeted fixes
Scaffold a new TypeScript Agent SDK runner in the current project — generates the runner class, types file, constants, and hooks directory with working examples
Fetch the latest Claude Agent SDK TypeScript documentation online, compare it against this plugin's reference files, and apply updates for any new options, hook events, message types, or behavioral changes. Run this periodically to keep the plugin accurate.
You are an expert architect specializing in TypeScript Claude Agent SDK platforms. Your role is to analyze SDK platform implementations and provide actionable architectural guidance.
You are a TypeScript Agent SDK hook strategy specialist. You design and implement complete, production-quality hook systems for Agent SDK platforms.
Use this skill when controlling agent behavior in TypeScript Agent SDK platforms — restricting allowed tools, setting budget and turn limits, crafting system prompts that guide agents to specific behaviors, implementing the file pre-creation pattern, augmenting prompts with runtime context, building message loggers, or tracking agent run metadata (cost, duration, iterations).
Use this skill when implementing TypeScript hook callbacks for the Claude Agent SDK — creating PreToolUse hooks to allow/deny tool calls, PostToolUse hooks to inject additionalContext, building factory functions for parameterized hooks, using HookCallback and HookJSONOutput types, applying isPreToolUseInput and isPostToolUseInput type guards, or designing a hooks strategy for an Agent SDK platform. Hooks in the TypeScript SDK are async functions, NOT JSON config files.
Use this skill when developing TypeScript applications with the Claude Agent SDK (@anthropic-ai/claude-agent-sdk), implementing query() calls, configuring SDK options, handling streaming message iteration, working with SDKMessage and SDKResultMessage types, managing AbortSignal, passing custom env variables, or setting up the single-point-of-contact types file for SDK imports.
A Claude Code plugin that provides a structured 4-step workflow for software development: Ticket → Plan → Implement → Review.
# Inside Claude Code
/plugin marketplace add ItamarZand88/claude-code-agentic-engineering
/plugin install agi@claude-code-agentic-engineering
# Run the complete workflow in one command
/agi:all "Add OAuth integration with Google"
# 1. Create task ticket with codebase analysis
/agi:1_ticket "Add OAuth integration with Google"
# 2. Generate implementation plan
/agi:2_plan .claude/tasks/add-oauth-integration
# 3. Execute the plan
/agi:3_implement .claude/tasks/add-oauth-integration
# 4. Code review
/agi:4_review .claude/tasks/add-oauth-integration
Review artifacts in .claude/tasks/{task-name}/ between steps for best results.
# Chain commands with --continue flag
/agi:1_ticket "Add feature" --continue=plan # ticket + plan
/agi:1_ticket "Add feature" --continue=implement # ticket + plan + implement
/agi:1_ticket "Add feature" --continue=all # full workflow
| Command | Description |
|---|---|
/agi:1_ticket <description> | Create task ticket with codebase analysis |
/agi:2_plan <task_folder> | Generate implementation plan |
/agi:3_implement <task_folder> | Execute the plan |
/agi:4_review <task_folder> | Code review and QA |
/agi:all <description> | Run complete workflow |
/agi:checks | Run linting/type checks |
/agi:best-practices | Generate coding standards from PRs |
/agi:fix-pr-comments <pr> | Fix PR review comments |
The plugin uses 3 specialized agents:
All artifacts are organized in .claude/tasks/:
.claude/tasks/{task-name}/
├── ticket.md # Requirements
├── plan.md # Implementation plan
└── review.md # Code review
gh) for best-practices and fix-pr-comments commandsAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete developer toolkit for Claude Code
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement