Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By dot-do
Enforces a strict TDD workflow (Red-Green-Refactor) for features, bugfixes, and refactors, while guiding collaborative brainstorming to refine ideas into validated designs through questions and trade-off exploration before coding.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-1 --plugin dot-do-workersTrack work with beads issue tracker using TDD workflow (RED/GREEN/REFACTOR phases)
Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation.
Comprehensive parallel code review with 5 specialized agents (general, architectural, TypeScript, product/vision, TDD/beads)
Use when implementing any feature or bugfix. Enforces RED-GREEN-REFACTOR cycle.
Track work with beads issue tracker using TDD workflow. Create issues for RED (failing tests), GREEN (implementation), and REFACTOR phases.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Comprehensive parallel code review using 5 specialized subagents: general, architectural, TypeScript, product/vision, and TDD/beads compliance
Complete development lifecycle: brainstorm → TDD planning → ralph implementation → review → feedback loop until approved
Use when implementing any feature or bugfix, before writing implementation code
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI team orchestration. Give Claude Code an AI team — CTO, Engineer, QA, Designer work together while you watch.
Lean agent skills for building, shipping, strategy, and growth — no context bloat.
Dynamic task-based agentic delegation with builder/validator pairs and meta-prompt team orchestration
75 specialized AI agents across Engineering, Product, Infrastructure, Data, Security, Marketing, Sales, Finance, Legal, and People. Automatic routing to the right specialist.
Claude Code multi-agent team orchestration (Chinese version). Set up parallel AI agent teams with file-based planning and role-based collaboration.
AI Agent Team Operating System for Claude Code — persistent team management, meetings, task wall, company loop engine, and real-time dashboard
Development lifecycle outer loop: brainstorm → TDD planning → ralph implementation → review → feedback loop until approved
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Share bugs, ideas, or general feedback.
AI + Code Workers
.dowork for you.
import { priya, ralph, tom, mark } from 'agents.do'
priya`plan the Q1 roadmap`
ralph`build the authentication system`
tom`review the architecture`
mark`write the launch announcement`
workers.do is the platform for building Autonomous Startups. Your workers are AI agents and humans—and they run on Cloudflare Workers.
Both kinds of workers. Working for you.
You need a team, but you're early. Maybe it's just you.
import { product, engineering, marketing } from 'teams.do'
const mvp = await product`define the MVP`
const app = await engineering`build ${mvp}`
await marketing`launch ${app}`
That's your startup. Running.
| Agent | Role |
|---|---|
| Priya | Product—specs, roadmaps, priorities |
| Ralph | Engineering—builds what you need |
| Tom | Tech Lead—architecture, code review |
| Rae | Frontend—React, UI, accessibility |
| Mark | Marketing—copy, content, launches |
| Sally | Sales—outreach, demos, closing |
| Quinn | QA—testing, edge cases, quality |
Each agent has real identity—email, GitHub account, avatar. When Tom reviews your PR, you'll see @tom-do commenting.
import { priya, ralph, tom, mark, quinn } from 'agents.do'
await priya`what should we build next?`
await ralph`implement the user dashboard`
await tom`review the pull request`
await mark`write a blog post about our launch`
await quinn`test ${feature} thoroughly`
No method names. No parameters. Just say what you want.
const spec = await priya`spec out user authentication`
const code = await ralph`build ${spec}`
const reviewed = await tom`review ${code}`
const docs = await mark`document ${reviewed}`
Or pipeline an entire sprint:
const sprint = await priya`plan the sprint`
.map(issue => ralph`build ${issue}`)
.map(code => tom`review ${code}`)
The .map() isn't JavaScript's—it's a remote operation. The callback is recorded, not executed. The server receives the entire pipeline and executes it in one pass.
Complex processes run themselves:
import { on } from 'workflows.do'
import { priya, ralph, tom, quinn, mark, sally } from 'agents.do'
on.Idea.captured(async idea => {
const product = await priya`brainstorm ${idea}`
const backlog = await priya.plan(product)
for (const issue of backlog.ready) {
const pr = await ralph`implement ${issue}`
do await ralph`update ${pr}`
while (!await pr.approvedBy(quinn, tom, priya))
await pr.merge()
}
await mark`document and launch ${product}`
await sally`start outbound for ${product}`
})
Event-driven. PR-based. Real development workflow.
AI does the work. Humans make the decisions.
import { legal, ceo } from 'humans.do'
const contract = await legal`review this agreement`
const approved = await ceo`approve the partnership`
Same syntax. Messages go to Slack, email, or wherever your humans are. Your workflow waits for their response.
Define your entire startup:
import { Startup } from 'startups.do'
import { engineering, product, sales } from 'teams.do'
import { dev, sales as salesWorkflow } from 'workflows.do'
export default Startup({
name: 'Acme AI',
teams: { engineering, product, sales },
workflows: { build: dev, sell: salesWorkflow },
services: ['llm.do', 'payments.do', 'org.ai'],
})
That's a company. It builds products, sells them, and grows.
Everything you need to run a startup:
| Service | What It Does |
|---|---|
| database.do | AI-native data with cascading generation |
| functions.do | Code, Generative, Agentic, Human functions |
| workflows.do | Event-driven orchestration |
| triggers.do | Webhooks, schedules, events |
| searches.do | Semantic & vector search |
| actions.do | Tool calling & side effects |
| integrations.do | Connect external services |
| analytics.do | Metrics, traces, insights |
| payments.do | Stripe Connect billing |
| services.do | AI-delivered service marketplace |
| org.ai | Identity, SSO, users, secrets |
| builder.domains | Free domains for builders |
import { llm } from 'llm.do'
import { payments } from 'payments.do'
import { org } from 'org.ai'
await llm`summarize this article`
await payments.charge(customer, amount)
await org.users.invite(email)
workers.do runs on Cloudflare Workers—the fastest serverless runtime.