</>MCP Agents Market
Plugin

plannotator

by backnotprop8kTypeScriptUpdated 2026-08-24

Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.

Claude CodeAmpCodexCopilot CLIDroidGemini CLIKiroOpenCode

Plannotator is a browser-based review tool for AI coding agents, packaged as a Claude Code plugin and available for Amp, Codex, Copilot CLI, Droid, Gemini CLI, Kiro, OpenCode, and Pi. It intercepts agent plans and opens them in your browser for annotation and markup, then sends your feedback directly back to the agent for revision. The plugin also provides code review capabilities for local changes and remote pull requests, with inline commenting and diff visualization. Developers can annotate markdown documents, HTML artifacts, and agent messages, creating a human-in-the-loop workflow for agent-assisted development.

Key Features

Automatic plan interception via agent hooks – opens plans in browser for annotation before implementation
Visual code review UI with side-by-side diffs, file trees, and inline commenting for Git, GitButler, Jujutsu, GitHub, and GitLab
One-click feedback loop – send annotations and comments directly to the agent as structured input
HTML artifact annotation with visual markup on rendered pages
Terminal-based review via Herdr Annotate plugin for command-line workflows
Team sharing with encrypted links and optional Workspaces for collaboration
VS Code and Obsidian integrations for viewing plans in editor tabs and saving to vaults
Privacy-first design with local storage, no telemetry, and optional encrypted sharing

Use Cases

  • 01Review and annotate AI agent implementation plans before code is written
  • 02Provide structured feedback on agent-generated code diffs and pull requests
  • 03Collaborate with teammates by sharing annotated plans and importing their feedback
  • 04Annotate product requirements documents, specifications, and technical documentation for agent context
  • 05Review GitButler workspaces, stacks, and branch layers with visual diff tools
  • 06Inspect and mark up HTML artifacts generated by agents before deployment

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.1k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin84.9k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.1k

plannotator — FAQ

What is Plannotator?+

Plannotator is a local browser-based review interface for AI coding agents that lets you annotate plans, review code diffs, and send feedback directly back to your agent. It works with Claude Code, Amp, Codex, Copilot CLI, Droid, Gemini CLI, Kiro, OpenCode, and Pi.

How do I install the Plannotator Claude Code plugin?+

In Claude Code, run '/plugin marketplace add backnotprop/plannotator', then '/plugin install plannotator@plannotator', and restart Claude Code. The installer script (curl -fsSL https://plannotator.ai/install.sh | bash) also auto-detects installed agents and configures hooks for macOS, Linux, WSL, and Windows.

Which AI clients does Plannotator support?+

Plannotator supports Claude Code, Amp, Codex, Copilot CLI, Droid, Gemini CLI, Kiro CLI, OpenCode, and Pi. Each agent requires specific setup steps documented in the installation guide, though the universal installer handles most configurations automatically.

Does Plannotator require API keys or send data to external servers?+

No API keys are required for core functionality. Plannotator stores all plans, annotations, and history locally by default with no telemetry. Optional features like URL annotation (via Jina Reader), Ask AI, and encrypted link sharing do contact external services, but these are opt-in and documented in the privacy policy.

Is Plannotator free to use?+

Yes, Plannotator is open source and dual-licensed under Apache 2.0 or MIT. All core features including plan review, code review, and local annotation are free. The hosted Workspaces product for team collaboration is separate and on a waitlist.

Can I use Plannotator in remote SSH or devcontainer environments?+

Yes, Plannotator auto-detects SSH sessions and switches to a fixed port (default 19432). For VS Code devcontainers, port forwarding happens automatically. For manual SSH, forward the port in your ~/.ssh/config with LocalForward 9999 localhost:9999.

How do I install plannotator?+

Open the source repository on GitHub and follow its README. plannotator is a plugin — MCP Agents Market links you directly to the official repo.

Is plannotator free?+

plannotator is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Code Review PluginsDeveloper Tools PluginsProductivity & Workflow PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories