https://github.com/rp1-run/rp1
Ready Player One - stop prompting; start shipping
https://github.com/rp1-run/rp1
ai claude-code context-engineering developer-tools opencode prompt-engineering
Last synced: about 12 hours ago
JSON representation
Ready Player One - stop prompting; start shipping
- Host: GitHub
- URL: https://github.com/rp1-run/rp1
- Owner: rp1-run
- License: apache-2.0
- Created: 2025-11-30T23:45:13.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2026-03-26T22:35:03.000Z (about 1 month ago)
- Last Synced: 2026-03-26T23:34:52.076Z (about 1 month ago)
- Topics: ai, claude-code, context-engineering, developer-tools, opencode, prompt-engineering
- Language: TypeScript
- Homepage: https://rp1.run
- Size: 17.8 MB
- Stars: 13
- Watchers: 0
- Forks: 3
- Open Issues: 50
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
- Agents: AGENTS.md
Awesome Lists containing this project
README
Ready Player One
> stop prompting; start shipping
Professional development workflows for AI coding assistants.
39 commands. 49 specialized agents. Single-pass execution.
Works today with Claude Code. Experimental support for OpenCode and Codex CLI.
---
## Why rp1?
**Single-pass execution** — Constitutional prompts encode expert patterns with built-in rules. No iteration loops, no "let me revise that" — tasks complete in one shot.
**Codebase awareness** — Run `knowledge-build` once. Your architecture becomes context for every command. No generic advice — everything respects your patterns.
**Lean context architecture** — Progressive disclosure and subagent delegation keep your main thread focused. Complex work happens in specialized agents, results flow back clean.
**Validate before you build** — Hypothesis testing catches bad assumptions early. Design decisions get validated against your codebase before implementation begins.
**Start anywhere** — Full blueprints with charters and PRDs, or jump straight in with a vague idea. Structured when you need it, flexible when you don't.
---
## Quick Start
### 1. Install the CLI
```bash
# macOS / Linux (Homebrew)
brew install rp1-run/tap/rp1
rp1 install
# Windows (Scoop)
scoop bucket add rp1 https://github.com/rp1-run/scoop-bucket
scoop install rp1
rp1 install
# Or use the install script
curl -fsSL https://rp1.run/install.sh | sh
```
Homebrew and Scoop install the rp1 CLI binary. Run `rp1 install` next to install integrations into detected host tools, then run `rp1 verify` to confirm the installation. The standalone install script already attempts the `rp1 install` step automatically.
### 2. Initialize your project
```bash
cd your-project
rp1 init
```
This will set up rp1 and install plugins for your AI assistant (Claude Code, OpenCode, or Codex CLI).
### 3. Restart your AI tool and run
```bash
/knowledge-build # Generate your codebase knowledge base
```
**[Full installation guide →](https://rp1.run/getting-started/installation/)**
---
## Beta Releases
Want to try upcoming features before they're officially released?
### Install Beta
```bash
brew install rp1-run/tap/rp1-beta
rp1 install
```
> **Note:** You cannot have both stable and beta installed simultaneously. Installing one requires uninstalling the other first.
### Verify
```bash
rp1 --version
# Should show a pre-release version like 0.7.0-beta.1
```
### Rollback to Stable
```bash
brew uninstall rp1-beta && brew install rp1-run/tap/rp1
rp1 install
```
---
## What Can You Do?
### Ship a feature
```bash
/build user-auth
```
### Review a PR
```bash
/pr-review "feature/auth"
```
### Investigate a bug
```bash
/code-investigate "bug-123" "Login fails intermittently"
```
### Quick code check
```bash
/code-check
```
**[See all 39 commands →](https://rp1.run/reference/)**
---
## Principles
| | |
|---|---|
| **Batteries Included** | Skills, subagents, 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, Codex CLI, and more coming. |
---
## Platform Support
| Platform | Status |
|----------|--------|
| [Claude Code](https://claude.ai/code) | Available |
| [OpenCode](https://opencode.ai) | Experimental |
| [Codex CLI](https://github.com/openai/codex) | Experimental |
| Cursor, Goose, Amp | Coming Soon |
---
## Guides
- **[Feature Development](https://rp1.run/guides/feature-development/)** — End-to-end workflow from requirements to verified implementation
- **[Bug Investigation](https://rp1.run/guides/bug-investigation/)** — Systematic root cause analysis with evidence-based hypothesis testing
- **[PR Review](https://rp1.run/guides/pr-review/)** — Thorough multi-pass analysis with visual diagrams
- **[Team Onboarding](https://rp1.run/guides/team-onboarding/)** — Get new developers productive on your codebase fast
---
## Contributing
See the [documentation](https://rp1.run) for architecture and contribution guides. Issues and PRs welcome!
## License
Apache 2.0 — See [LICENSE](LICENSE)
---
Documentation ·
Issues ·
Releases
