bloomery

Community

Craft a coding agent with raw HTTP calls.

Authormgratzer
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The Bloomery Skill provides a hands-on guide to building a coding agent from scratch using raw HTTP calls to an LLM API, enabling engineers to learn the mechanics behind agentic loops, memory, and tooling without relying on SDKs.

Core Features & Use Cases

  • Step-by-step tutorial to scaffold a working coding agent in roughly 300 lines of code.
  • Demonstrates a full agent toolkit: a multi-step conversational loop, a system prompt, and essential tools such as list_files, read_file, and run_bash.
  • Covers Gemini, OpenAI (and compatible endpoints), and Anthropic, with TypeScript, Python, Go, and Ruby as target languages.

Quick Start

Run the scaffold script to generate your agent scaffold and begin Step 0.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: bloomery
Download link: https://github.com/mgratzer/bloomery/archive/main.zip#bloomery

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.