Code review
A diff per task with accept, reject and comment — plus a built-in editor with Git support.
Agents are confident and sometimes wrong. Reviewing their work in a separate Git client breaks your flow and hides the reasoning behind each change.
Nothing lands because an agent said it was done. Every task produces a diff you can read in the app. Accept it, reject it, or leave a comment and send it back — the agent picks the comment up and revises. Reviewer agents can do the first pass so you only see what survived.
- Per-task diff view, file by file
- Accept, reject, or comment and send back
- Reviewer agents do the first pass
- Built-in editor with Git support
- Comments become the agent's next instruction
Workflows that lean on code review
- For teams drowning in small stuff
Clear a backlog of small tasks overnight
Point a team at thirty low-risk tickets and wake up to thirty diffs waiting for review.
- For anyone who inherited the code
Refactor a legacy codebase without breaking it
Split the refactor across agents, block risky work behind tests, and review every diff before it lands.
- For the person who has to fix the number
Raise test coverage on a project nobody tested
One agent per module, tests written in parallel, every suite run in the built-in terminal before review.
- Use caseRefactor a legacy codebase without breaking itSplit the refactor across agents, block risky work behind tests, and review every diff before it lands.
- Use caseShip a product as one person with a team of agentsStart in solo mode, promote to a team when the work outgrows one agent, and keep the spend capped.
- ComparisonAgentTeams vs Claude Code CLIAnthropic's terminal-first coding agent.
Stop being the message bus.
Install it, open a repo, and give three agents an objective. Free, no account, no API key.