Plugin · Claude Code · AI Agents

Tbdng Compound Teams Plugin

tbdng-compound-teams-plugin is a Claude Code plugin for the Build phase that orchestrates agent teams, Ralph loops, and compound learning as a repeatable coding-factory workflow.

by tbdng · github.com/tbdng/compound-teams-plugin

Run a repeatable Claude Code factory loop—team roles, Ralph iteration, multilens review, and compound learnings across real engineering tasks.

0
GitHub stars
0
Installs
0
Community votes
One vote per signed-in builder - it helps surface the tools the community actually relies on.
Install

Add it to Claude Code

Install the plugin in Claude Code. One command, paste-ready.

Install the plugin
/plugin install tbdng-compound-teams-plugin@tbdng/compound-teams-plugin
Add to ClaudeUse the Agent APISkillselion is itself an MCP server - your agent can fetch this config directly.
Agent API

Built to be called by your agent

Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.

Retrieve this entry with skillselion.get_details("plugin:tbdng/compound-teams-plugin") and the paste-ready config with skillselion.get_install_config("plugin:tbdng/compound-teams-plugin").

About

What it does

tbdng-compound-teams-plugin is a Claude Code plugin that packages a coding-factory workflow: coordinate agent teams, run Ralph-style iteration loops, and compound learnings so each project gets faster and more consistent. Solo builders who already lean on Claude Code for implementation install it when ad-hoc prompting is not enough—they want named phases (plan, quick spike, build, review, compound) invoked as commands rather than reinventing process every sprint. The plugin emphasizes execution discipline—setup, planning shortcuts, build runs, multilens review, and knowledge extraction—so agents do not drift between tasks. It suits multi-file features, refactors, and greenfield modules where retry-until-green and structured review reduce rework. It is heavier than a single skill: expect to adopt the command vocabulary and let compound learning accumulate patterns in your repo over time.

Highlights

  • Bundled workflow commands: ctsetup, ctplan, ctquick, ctbuild, ctreview, and ctcompound for end-to-end runs
  • Agent Teams pattern for parallel roles plus Ralph Loops for retry-until-green execution
  • Compound Learning flow to capture and reuse engineering learnings across projects
  • Multilens review and structured review passes before merge-quality output
  • Embedded skills and CLAUDE.md-oriented setup for persistent project context

Why builders use it

Solo builders lose speed when every feature is a one-off chat with no team roles, no retry discipline, and no retained learnings between sessions.

After install, you run named ct* commands through plan-build-review-compound cycles so Claude Code executes as a factory line and past learnings feed the next task.

At a glance

  • Type - Plugin in AI Agents.
  • Adoption - 0 installs, 0 stars, 0 votes.

FAQ

Who is tbdng-compound-teams-plugin for?

It is for solo and small-team builders using Claude Code who want agent teams, iterative Ralph loops, and compound learning instead of unstructured multi-hour sessions.

When should I use tbdng-compound-teams-plugin?

Use it when starting a non-trivial feature or refactor and you are ready to run ctsetup → ctplan or ctquick → ctbuild → ctreview → ctcompound as your default delivery loop.

How do I add tbdng-compound-teams-plugin to my agent?

Install the plugin from the compound-teams-plugin marketplace entry into Claude Code, run ctsetup in your project, then invoke the ct* slash commands from the embedded command set.

Discussion

Comments

Share how you use tbdng-compound-teams-plugin, gotchas, or tips for other indie builders.

No comments yet - be the first to share how you use it.

This week for builders

Five minutes, every Monday — the tools, releases and tactics for shipping solo.

unsubscribe anytime.