Quick Start

In 15 minutes you will go through the full Brewcode cycle: from project analysis to launching an infinite task. By the end you will have a specification, a plan, and a running task with automatic context handoff.

Before you begin

Make sure Claude Code and the brewcode plugin are installed. If not, follow the instructions in Installation.

Full workflow

  1. Project setup/brewcode:setup

    Open Claude Code in your project root and run:

    /brewcode:setup

    What happens: the skill analyzes your project structure, tech stack, test frameworks, and existing agents. It generates tailored templates based on the analysis.

    Result:

    • .claude/tasks/templates/PLAN.md.template — plan template
    • .claude/tasks/templates/SPEC.md.template — specification template
    • .claude/tasks/cfg/brewcode.config.json — configuration
    • .claude/skills/brewcode-review/tailored code review skill

    This step runs once per project.

  2. Creating a specification/brewcode:spec

    Describe the task in plain text or point to a requirements file:

    /brewcode:spec “Implement JWT authorization with role-based access”

    Or from a file:

    /brewcode:spec ./docs/requirements/auth.md

    What happens: the plugin launches 5-10 research agents in parallel. The agents analyze the codebase, find related code, dependencies, and patterns. Then it asks clarifying questions (use the -n flag for autonomous mode without questions).

    Result: a SPEC.md file — a structured specification with project context.

  3. Generating a plan/brewcode:plan
    /brewcode:plan

    What happens: a phased execution plan is generated from SPEC.md. Each phase contains specific steps, expected artifacts, and completion criteria.

    Result: a PLAN.md file — a plan with phases, ready for execution.

  4. Running the task/brewcode:start
    /brewcode:start

    What happens: Brewcode begins executing the plan phase by phase. Agents work on the task, recording knowledge in KNOWLEDGE.jsonl. When context reaches ~90%, the PreCompact hook fires: knowledge is compressed, handoff state is written, and the session continues automatically.

    Result: the task runs to completion regardless of how many compaction cycles occur. All artifacts are saved in .claude/tasks/<ts>_<name>_task/artifacts/.

What’s next

After the task completes

The task is done. Here is what you can do with the results:

Code review — run a quorum review of the changes:

/brewcode:standards-review

Extract rules — convert accumulated knowledge into project rules:

/brewcode:rules

Prompt optimization — reduce tokens in prompts and agents:

/brewtools:text-optimize

All skills

🏛

brewcode

13 skills for development: infinite tasks, review, semantic search, skill and agent creation, dynamic teams.

🔧

brewtools

6 skills for text utilities: prompt optimization, AI artifact removal, secrets scanning, SSH, deploy.

🖼️

brewui

2 skills for UI/visual/creative tools: AI image generation, design-to-code.

📄

brewdoc

6 skills for documentation: automatic sync with the codebase, doc generation, memory optimization, PDF conversion, publishing.

📋

All brewcode skills

Full list of 13 brewcode skills with commands, parameters, and dependencies.

👥

Dynamic teams

Create 5-20 project-specific agents with self-selection and performance tracking.

🚀

Latest Release

Download, changelog, and installation instructions.

🔗

View on GitHub

Source code, README, and configuration files.