The problem
Without a tool like monocle, reviewing agent-written code means rubber-stamping diffs you didn’t read, copy-pasting feedback into a chat window, or just hoping the agent got it right. There’s no way to say “fix these three issues and show me again.” monocle gives you a proper review loop without slowing the agent down. It doesn’t gate each file change behind an approval — your agent keeps working while you review at your own pace. When you’re ready, leave line-level comments and submit. You see the updated diffs, review again, and iterate.Supported agents
monocle works with any coding agent that supports agent skills or can call CLI commands:Key capabilities
Real-time diff review
Watch diffs appear as your agent writes code. Unified and split views with syntax highlighting and intra-line diffs.
Line-level comments
Tag feedback as issues, suggestions, notes, or praise — at the line or file level. Propose exact code changes with suggestion blocks.
Structured review submission
Submit all comments in one batch. Your agent receives the formatted review immediately and starts addressing your feedback.
Plan and architecture review
Review your agent’s plans and architecture decisions before it writes code, not just the output.
Push notifications
With Claude Code and MCP channels, feedback is pushed directly into the agent’s context the moment you submit.
Review gating
Block the agent until you approve submitted content using the
/review-plan-wait skill.How it works
- Your agent writes code — monocle shows you the diffs in real time.
- You navigate with
j/k, add comments withc, and submit withS. - monocle queues your review for delivery.
- The agent picks up your feedback — immediately via push notification (Claude Code with MCP channels) or on the next poll — and starts making fixes.
- You see the updated diffs, review again, and iterate.
Next steps
Installation
Install monocle via Homebrew or pre-built binaries.
Quick start
Register monocle with your agent and start your first review session.