waldzellai

Fast Agent TypeScript — Testing skill for Claude Code

Testing community

Define, Prompt and Test MCP enabled Agents and Workflows.

How to install Fast Agent TypeScript

This entry records only its repository, not the path inside it, so there is no exact command to give. Open waldzellai/fast-agent-typescript and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Fast Agent TypeScript does

Define, Prompt and Test MCP enabled Agents and Workflows. TS Fork.

Alternatives in Testing

  • Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
  • OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
  • Sentient — Test prompt to showcase claude code hook blocking a dangerous rm -rf command 3.4k ★

README

npm version discord NPM Downloads

Overview

[!TIP] Documentation site is in production here : https://fast-agent.ai. Feel free to feed back what's helpful and what's not. There is also an LLMs.txt [here](https://fast-agent.ai/llms.txt)

**`fast-agent-typescript`** enables you to create and interact with sophisticated Agents and Workflows in minutes. It is the first framework with complete, end-to-end tested MCP Feature support including Sampling. Both Anthropic (Haiku, Sonnet, Opus) and OpenAI models (gpt-4o/gpt-4.1 family, o1/o3 family) are supported.

The simple declarative syntax lets you concentrate on composing your Prompts and MCP Servers to [build effective agents](https://www.anthropic.com/research/building-effective-agents).

`fast-agent-typescript` is multi-modal, supporting Images and PDFs for both Anthropic and OpenAI endpoints via Prompts, Resources and MCP Tool Call results. The inclusion of passthrough and playback LLMs enable rapid development and test of TypeScript glue-code for your applications.

[!IMPORTANT] The fast-agent documentation repo is here: https://github.com/evalstate/fast-agent-docs. Please feel free to submit PRs for documentation, experience reports or other content you think others may find helpful. All hel

Related Skills

Smoke Test — Testing skill for Claude Code

Smoke Test

Give me prompts to test in the F5 window that opens in C:\GameDev\iemis repo. They should test the features yo

Testing community
Godspeed — Testing skill for Claude Code

Godspeed

Routing classifier + multi-agent orchestrator for Claude Code. 3-4ms Node fast-path hook, per-prompt S0-S5 tie

Testing community
Outlook LLM Tests — Testing skill for Claude Code

Outlook LLM Tests

Run make crud-test from the repository root via the Bash tool. This is the primary, canonical way to execute t

Testing community
Test Full — Testing skill for Claude Code

Test Full

Run the full test suite across all tox environments with coverage enabled.

Testing community
Get Shit Done Multi — Testing skill for Claude Code

Get Shit Done Multi

Fork of Get Shit Done (TÂCHES) with multi-CLI support. Spec-driven development workflows for Claude, Copilot,

Testing community
Cfn E2e — Testing skill for Claude Code

Cfn E2e

MUST BE USED instead of running Playwright tests directly in WSL2. Parallel E2E execution, auto-batches tests

Testing community

Related Agents

Skill Portfolio Analyzer — Development agent for Claude Code

Skill Portfolio Analyzer

Analyzes installed skills/plugins/MCP servers against ~/.claude.json to detect dead, ghost, duplicate, and col

Development community
Unity Prototyper — Testing & QA agent for Claude Code

Unity Prototyper

The star agent. Rapid end-to-end prototyping — given a mechanic description, writes C# scripts, builds the tes

Testing & QA community
Claude Code MCP Behavior Analysis — Research agent for Claude Code

Claude Code MCP Behavior Analysis

Results from 15 tests against a minimal Cord MCP server. Tested: Claude Code 2.1.37, 2026-02-18. Note: These t

Research community