plannotator: what it is, what problem it solves & why it's gaining traction

What it solves

Plannotator provides a visual review surface for AI coding agents. It solves the problem of reviewing complex plans, code diffs, and HTML artifacts in a terminal-based agent interface, allowing users to mark up and send feedback directly back to the agent for iteration.

How it works

Plannotator plugs into AI agents (such as Claude Code, Copilot CLI, and Gemini CLI) via hooks and commands. When an agent proposes a plan or writes code, Plannotator opens a local browser-based UI. The user can annotate the content, approve or deny the plan, and send structured feedback. The agent then receives this feedback and revises its work based on the user's comments.

Who it’s for

Developers using AI coding agents who want a more intuitive, visual way to review and iterate on agent-generated plans and code changes before they are implemented.

Highlights

• Multi-Agent Support: Integrates with Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, Kiro, Droid, Amp, and Pi.
• Visual Annotation: Support for annotating Markdown plans, HTML artifacts, and code diffs.
• Code Review: Integrated diff viewer for local changes or remote PRs (GitHub/GitLab) with the ability to suggest code.
• Collaboration: Ability to share plans via encrypted links for teammate feedback.
• Editor Integrations: Extensions for VS Code, Obsidian, and Bear to save or view plans.
• Security: SLSA provenance attestations for binary verification.