Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By Automattic
Automate software development from intent to documentation through a multi-phase agent pipeline that produces specs, designs, code, and docs with adversarial reviews at each stage.
Adversarially review the code plan produced for a Radical Pipelines task for completeness, feasibility, and alignment with the spec and design
Produce the code plan for a Radical Pipelines task
Adversarially review a batch of completed code-writer tasks against the code plan, spec, and design — once, after all tasks in the batch have committed
Execute one task from the code plan with test-driven development, producing code and tests that satisfy the task's acceptance criteria
Drive iterative Q&A with the design-doc-researcher to work through the design and record design-doc-research.md
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. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An agent orchestrator that runs teams of agents autonomously through a pipeline of defined phases, where each phase produces concrete, inspectable artifacts.
Today, most of us use agents in what we'd call "assisted mode". We give them a rough idea, they start implementing, and we sit next to them correcting the course along the way. This works, but it's a workaround for two structural gaps, not a deliberate workflow.
The first is the lack of requirements. Without clear specs, the agent picks a direction and the human has to steer it in real time. But agents are already capable of implementing autonomously if the requirements are well-defined. Assisted mode is a workaround for missing requirements, not a limitation of the agents themselves.
The second is the lack of determinism. Agent output is non-deterministic. The same prompt, the same context, can produce a different result every time. So even when the human knows exactly what they want, they still assist because the agent might take a bad path this particular run.
Beyond that:
Assisted mode has no structure. There's no systematic process that guarantees the right assets get produced. Whether tests, documentation, or other artifacts get generated depends entirely on the human remembering to ask for them.
Assisted mode is inherently local. The context built up along the way, the decisions made, and the intermediate output only exist on the machine of the person doing the work. The final PR is the only thing the team gets to see, which makes it hard to coordinate or have multiple people work on the same task.
An agent orchestrator that runs teams of agents autonomously through a pipeline of defined phases. Each phase produces concrete, inspectable assets, and the pipeline can run partially or fully without human intervention.
The phases are:
The pipeline is autonomous by default, assisted when needed. It runs on its own, but humans can intervene at any checkpoint. For particularly complex tasks, specific phases can be run in assisted mode instead.
It is inspectable and relaunchable. Every phase produces artifacts your team can review. If the output at any point isn't what the team expected, anyone on the team can go back to the phase where the assumptions diverged, correct them, and relaunch the autonomous sequence from there.
It can add determinism through redundancy. For complex tasks, you should be able to spend more tokens on the same surface with multiple runs, validation checks, adversarial agents, and different models from different providers to converge on a more reliable output.
Create WordPress block themes from simple descriptions and deploy them to a local WordPress Studio site, or, generate professional themes through an interactive workflow: describe your site, choose from design options, and preview on a real WordPress installation.
Create WordPress block themes from simple descriptions and deploy them to a local WordPress Studio site. Generate professional themes through an interactive workflow: describe your site, choose from design options, and preview on a real WordPress installation.
Craft production-grade WordPress sites and applications. Everything from themes and plugins to commerce and deployment.
Extract content from closed web platforms (GoDaddy Websites & Marketing, Hostinger, HubSpot, Shopify, Squarespace, Webflow, Weebly, Wix) into WordPress-compatible WXR files. Inspect, extract, QA, and import to WordPress.
Manage domains from Claude Code — check availability, register, configure DNS, and more via the dn CLI
npx claudepluginhub automattic/radical-pipelinesUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.