Quick Start

Establish project conventions and domain agents, then prepare a task board, specification and project-tailored review skill. Run setup generators in separate sessions.

Before you begin

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

A skill whose name ends in -setup installs a mechanism you use afterwards instead of the skill itself; recurring tools keep bare names. The full ordered list lives in Full Setup.

Distributed plugin skills require your explicit command, with three exceptions: Claude can run /brewdoc:publish (“publish this”, “share a link”), /brewtools:text-optimize and /brewtools:text-human on its own mid-task; typing them still works. Generated project skills can be model-invocable. Each setup generator works best in its own fresh session.

Full workflow

  1. Install the workflow pluginsplugin install

    Add the marketplace and install Brewcode plus Brewtools for the task board:

    claude plugin marketplace add https://github.com/kochetkov-ma/claude-brewcode
claude plugin install brewcode@claude-brewcode
claude plugin install brewtools@claude-brewcode

    This step runs once per machine. Reload with /reload-plugins if already inside a session.

  2. Set up project conventions/brewcode:convention-setup
    /brewcode:setup-status
/brewcode:convention-setup install

    What happens: parallel agents analyze each architectural layer, extract etalon classes, coding, testing and architecture patterns, and write them into .claude/convention/ with reversible loading guidance.

    Follow the setup dashboard’s order: search foundation when applicable, then conventions before teams and review setup. Result: a written project reference for later agents.

  3. Create a domain agent team/brewcode:teams-setup
    /brewcode:teams-setup install core "one agent per bounded context, plus a migrations specialist"

    Generates 5-20 project-specific agents with self-selection logic and performance tracking. Use the convention foundation when generating the team. To remove a team later, name it: uninstall core, or purge core to drop its archive and trace files too.

  4. Set up the task board/brewtools:task-board-setup

    Run it once per repo and explicitly select the optional spec + design layer when asked:

    /brewtools:task-board-setup install . "one lane per service"

    Create the task first, then resolve that existing task by its unique title:

    /task-board add "Implement JWT authorization with role-based access"
/task-spec "Implement JWT authorization with role-based access"

    The board returns the actual task ID; use that ID with /task-spec if titles overlap. Task-spec requires an existing task record and does not create one. If the spec layer was omitted, run task-board setup’s upgrade and select it before invoking task-spec.

    What happens: task-board-setup analyzes the repo with parallel agents and deploys a file-based Kanban plus a project-tailored /task-spec skill. /task-spec researches the codebase, asks clarifying questions, and fans out to domain agents for system design.

    Result: a board with shared domain methodology and a task with its own methodology, spec and design under .claude/features/. When a top-level task becomes active, the main session’s task-board announces and creates its unique hourly session anti-drift cron, with a user-selected cadence or opt-out. Delivered ticks reconcile the graph and report progress; timers depend on the active session and runtime limits.

  5. Generate a deep review skill/brewcode:superreview-setup
    /brewcode:superreview-setup install "QUICK depth; gate on the existing build and lint commands"

    What happens: analyzes your codebase and conventions, then generates a project-tailored quorum review skill that merges code review and standards checking into one reusable skill installed locally at .claude/skills/.

    Result: a custom review skill ready to invoke any time you need a deep, project-aware code review.

What’s next

After the workflow

Your project is set up for iterative development. Here is what you can do next:

Deep review — generate the project’s own quorum review skill, then invoke the generated /superreview whenever you need it:

/brewcode:superreview-setup status

Extract rules — convert knowledge into project-wide coding rules. This skill takes a free-form instruction, so say what you want:

/brewcode:rules "derive rules from .claude/convention/ and the last 200 commits, one file per domain, no duplicates of CLAUDE.md"

Prompt optimization — reduce tokens in prompts and agents:

/brewtools:text-optimize .claude/agents/

brewcode mods — two optional add-ons, plan-mode effort and prompt placeholders, installed separately from the suite:

claude plugin install brewmod-plan-effort@claude-brewcode
claude plugin install brewmod-placeholders@claude-brewcode

All skills

🏛

brewcode

9 skills: semantic search, deep review, conventions, rules, teams, setup status, and more.

🔧

brewtools

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

🖼️

brewui

Placeholder for future UI/visual/creative tools (currently empty).

📄

brewdoc

5 skills for documentation: doc-staleness tracking, doc generation, memory-sync generation, PDF conversion, publishing.

📋

Full Setup

All 11 -setup skills in one ordered run list, with what each installs.

👥

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.

Updating plugins

Use /brewtools:plugin-update to check and update the brewcode plugin suite in one command. See the FAQ for details.