stop prompting; start shipping¶
Professional development workflows for AI coding assistants. Skip the iteration loops — single-pass workflows that get it right the first time. 21 commands. 18 specialized agents. Careful context management. Works today with Claude Code and OpenCode (experimental).
-
Feature workflow — requirements, design, tasks, build, verify
-
PR visualization — understand changes at a glance
-
Artifacts-driven development — structured documentation for every feature
Try it out¶
Ship a feature
Or for small well-scoped quick tasks (that don't need extensive planning):
Review a PR
Investigate a bug
Generate knowledge base
Quick code check
Strategic analysis
Why rp1?¶
Ship features without iteration loops
Constitutional prompts encode expert patterns with built-in rules. No "let me revise that" — tasks complete in one shot.
Get context-aware suggestions instantly
Run knowledge-build once. Your architecture becomes context for every command. No generic advice — everything respects your patterns.
Keep your AI focused, not overwhelmed
Progressive disclosure and subagent delegation offload complex work to specialized agents while keeping your main thread focused. This allows your workflows to run uninterrupted for hours if needed on complex tasks.
Catch bad assumptions before coding
Automatic hypothesis testing catches bad assumptions early. Design decisions get validated against your codebase before implementation begins.
Jump in with any level of planning
Full blueprints with charters and PRDs, or jump straight in with a vague idea. Structured when you need it, flexible when you don't.
Artifact-driven development
Understand what is being created, how it's being created, and why. Full transparency into the agent's thinking as work progresses. Artifacts also enable full resumability — workflows aren't tied to the agent's context window to remember state.
Parallelize work with git worktrees
Run multiple features simultaneously in isolated worktrees. No branch switching, no stashing — each task gets its own clean working directory.
rp1 Principles¶
Batteries Included
Skills, subagents, specialized agent tools, and finely-tuned prompts ship out of the box. No assembly required.
Always Open Source
Fully pluggable into existing agentic tools. Your workflows, your control.
Visual-First
Heavily leans on visual language — diagrams, charts, and structured outputs for clarity.
Continuous Evolution
Keep improving and adapting as frontier models mature. Today's best, tomorrow's baseline.
Model/Tool Agnostic
No lock-in to any frontier lab or platform. Works with Claude Code, OpenCode (experimental), and more tools coming.
Guides¶
PR Review
Thorough multi-pass analysis that catches what single-reviewer approaches miss. Visual diagrams show exactly what changed.
Team Onboarding
Get new developers productive on your codebase fast. Knowledge base + guided exploration beats reading docs alone.
Platform support¶
Coming soon: Cursor, Goose, Amp
