v0.1.10

User arguments for ralphs

Ralphs can now accept user arguments from the CLI, making them reusable across different projects and configurations.

Pass --name value flags or positional arguments to ralph run:

ralph run research --dir ./my-project --focus "performance"

Reference them in your RALPH.md with {{ args.name }} placeholders:

---
description: Research agent
args: [dir, focus]
---
Research the codebase at {{ args.dir }}.
Focus area: {{ args.focus }}

Context and check scripts receive user arguments as RALPH_ARG_<KEY> environment variables.

See the CLI reference and primitives docs for full details.

New documentation

• Quick reference — single-page cheat sheet for CLI commands, directory structure, frontmatter fields, and placeholders
• Prompt writing guide — best practices for writing effective RALPH.md prompts
• "How it works" — explains the iteration lifecycle and system model
• "When to use" — helps evaluate whether ralph loops fit your task
• Agent comparison table — side-by-side comparison of supported agents with output behavior notes
• Expanded cookbook — new recipes for Python, TypeScript, Rust, Go, bug fixing, codebase migration, and multi-ralph project setup

Fixed

• Malformed ralph.toml now shows a helpful error message instead of a raw KeyError.