agent-alchemy

agent
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 33 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This toolkit is a curated collection of plugins, apps, and extensions designed to extend AI coding assistants like Claude Code. It provides structured development workflows, including spec-driven development, autonomous task execution, and a real-time Kanban dashboard.

Security Assessment
Overall Risk: Low. The automated code scan of 12 files found no dangerous patterns and noted no hardcoded secrets. As a workflow orchestrator, the tool inherently relies on executing commands to run tests, interact with Git, and manage project files, which is standard for this category. It runs a local Next.js web server for its task manager, meaning it does make local network requests. However, it requires no dangerous system permissions, keeping the threat surface minimal.

Quality Assessment
Overall Quality: High. The project is actively maintained (last updated today) and uses the permissive MIT license. It has a solid foundation of community trust with 33 GitHub stars. The architecture is notably transparent; the plugins are built using plain markdown files, which means the instructions given to the AI agent are completely human-readable and easy to audit before use.

Verdict
Safe to use. It offers a transparent, actively maintained, and secure way to enhance your AI-assisted coding workflows.
SUMMARY

Agent Alchemy is a curated collection of plugins, apps, and extensions designed to elevate your agentic engineering workflows. Built for Claude Code and other AI coding agents, these tools help developers work smarter and ship faster.

README.md

Agent Alchemy

A plugin suite and developer toolkit that extends Claude Code into a structured development platform — from specs to tasks to autonomous execution.

What is Agent Alchemy?

Agent Alchemy is an open-source toolkit for AI and software engineers who use Claude Code. It adds structured development workflows on top of Claude Code through six plugins, a real-time task manager, and a VS Code extension — all designed to work together as an integrated pipeline.

Everything is built with Claude Code for Claude Code. The plugins are plain markdown — readable, editable, and version-controlled like any other code.

Components

Claude Code Plugins

Six plugin groups providing 28 skills and 16 agents:

Plugin Description
SDD Tools Spec-Driven Development — turn ideas into specs, specs into tasks, and tasks into autonomous execution
Dev Tools Feature development, code review, architecture patterns, documentation, and changelog management
Core Tools Codebase analysis, deep exploration with multi-agent teams, and language patterns
TDD Tools Test-Driven Development — RED-GREEN-REFACTOR workflows, test generation, and coverage analysis
Git Tools Conventional Commits automation
Plugin Tools Plugin porting, adapter validation, ported plugin maintenance, and ecosystem health analysis

Task Manager

A Next.js real-time Kanban dashboard for monitoring autonomous task execution. Tasks update live via filesystem watching and Server-Sent Events.

Claude Task Manager

See more screenshots screenshots below

VS Code Extension

Schema validation, YAML frontmatter autocomplete, and hover documentation for Claude Code plugin development.

Getting Started

Prerequisites

  • Claude Code CLI installed
  • Node.js >= 18.0.0
  • pnpm >= 8.0.0

Install Plugins

# Install from the Claude Code marketplace
claude plugins install agent-alchemy/agent-alchemy-sdd-tools
claude plugins install agent-alchemy/agent-alchemy-dev-tools
claude plugins install agent-alchemy/agent-alchemy-core-tools
claude plugins install agent-alchemy/agent-alchemy-git-tools
claude plugins install agent-alchemy/agent-alchemy-tdd-tools
claude plugins install agent-alchemy/agent-alchemy-plugin-tools

Run Task Manager

pnpm install
pnpm dev:task-manager
# Open http://localhost:3030

Build VS Code Extension

cd extensions/vscode
npm install
npm run build
npm run package

Configuration

Plugin behavior is configured via .claude/agent-alchemy.local.md — a markdown file with nested key-value pairs using key: value syntax. This file is not committed to version control.

File Format

- deep-analysis:
  - direct-invocation-approval: true
  - invocation-by-skill-approval: false
- execute-tasks:
  - max_parallel: 5
- author: Your Name
- spec-output-path: specs/

Settings Reference

Setting Plugin Default Description
deep-analysis.direct-invocation-approval core-tools true Require user approval of the team plan when invoking /deep-analysis directly
deep-analysis.invocation-by-skill-approval core-tools false Require approval when deep-analysis is loaded by another skill (e.g., /feature-dev, /codebase-analysis)
execute-tasks.max_parallel sdd-tools 5 Maximum concurrent task-executor agents per wave. CLI --max-parallel takes precedence. Set to 1 for sequential execution
author sdd-tools Author name for spec attribution and task metadata
spec-output-path sdd-tools specs/ Default directory for spec file output

Precedence

Settings follow this precedence order (highest to lowest):

  1. CLI arguments (e.g., --max-parallel)
  2. .claude/agent-alchemy.local.md settings
  3. Built-in defaults

Architecture

Agent Alchemy follows a markdown-as-code philosophy — "prompts as software" — where AI agent behaviors, workflows, and domain knowledge are defined entirely in Markdown with YAML frontmatter. There is no compilation step; the markdown files are the executable code, interpreted directly by Claude Code's runtime.

Three Interconnected Systems

Plugin Framework (claude/)        Task Dashboard (apps/task-manager/)
  28 skills, 16 agents              Next.js 16 + TanStack Query
  6 plugin groups                   Real-time Kanban via SSE
  markdown-as-code                  Watches ~/.claude/tasks/
         │                                    ▲
         │  creates task JSON files           │ watches filesystem
         └────────────────────────────────────┘

VS Code Extension (extensions/vscode/)
  Ajv YAML frontmatter validation
  7 JSON schemas
  Autocompletion + hover docs

The SDD Pipeline

The flagship workflow chains four skills into an end-to-end development pipeline:

/create-spec  →  specs/SPEC-{name}.md        (adaptive interview)
                      │
/analyze-spec →  {name}.analysis.md + .html   (quality gate)
                      │
/create-tasks →  ~/.claude/tasks/*.json       (dependency-ordered decomposition)
                      │
/execute-tasks → Wave-based autonomous execution → Task Manager (real-time)

Model Tiering

Tier Model Use Case
Reasoning Opus Synthesis, architecture, review, implementation
Exploration Sonnet Parallel search, broad codebase exploration
Simple Haiku Git commits, quick tasks

Tech Stack

Component Technology
Plugins Markdown + YAML frontmatter
Task Manager Next.js 16, React 19, TanStack Query 5, Tailwind CSS v4, Chokidar 5
VS Code Extension Ajv, esbuild
Package Manager pnpm (workspaces)

Repository Structure

claude/                          # Plugins (markdown-as-code)
├── core-tools/                  # Analysis & exploration
├── dev-tools/                   # Development lifecycle
├── sdd-tools/                   # Spec-Driven Development
├── tdd-tools/                   # Test-Driven Development
├── git-tools/                   # Git automation
└── plugin-tools/                # Plugin porting & ecosystem health

apps/task-manager/               # Real-time dashboard
├── src/lib/fileWatcher.ts       # Chokidar -> SSE
├── src/app/api/events/route.ts  # SSE endpoint
└── src/components/              # React UI

extensions/vscode/               # Developer tooling
├── src/frontmatter/             # YAML validation
└── schemas/                     # JSON Schemas for plugin contracts

Screenshots

Task Manager Kanban View

Claude Task Manager

Tasks Generated from sdd-tools

Spec Tasks

Single Task View with Dependencies, Test Cases and Acceptance Criteria

Task Detail View

Completed Tasks in Claude Code

Completed Tasks

License

MIT

Yorumlar (0)

Sonuc bulunamadi