Ordewell
Turn one goal into an ordered plan of coding-agent tasks
Ordewell turns one goal into an editable plan of coding-agent tasks. A read-only planner researches your repository, asks about anything unclear, and returns a dependency graph where each task names its agent, model and thinking effort. Independent tasks run in parallel in their own git worktrees, and nothing reaches your branch until you review it. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49712276
✨ The overview, FAQ and details below were drafted by AI from the product's own website and haven't been reviewed by the maker yet. Are you the maker? Claim this listing to review and edit them.
Overview
Who is it for?
Developers who run coding agents like Claude Code, Codex and OpenCode on larger changes.
Problem
Handing a big goal to one agent session is hard to review and often uses the wrong model for each part.
Solution
An ordered, editable task plan with per-task models, isolated branches and evidence-based completion.
What makes it unique
Completion is decided by a marker in the agent's output rather than the model's own judgment, and the planner can't modify your repo.
Ordewell FAQ
Which coding agents does it support?
Claude Code, Codex and OpenCode out of the box, and they can be mixed within one plan.
Do I need a separate API key?
No. A coding agent you already pay for can act as the planner, or you can use an API key from any of 25 providers.
Where can I use it?
A terminal UI, a VS Code extension and a CLI.
Details
- Pricing
- Open Source
- Categories
- Coding & Dev ToolsAI Agents
- Built for
- Developers
- Platforms
- CLIVS Code
Compare Ordewell
Hunted by AI Launch Team
Discussion (0)
Sign in to join the discussion.