#99 · Primary category: AI Coding Assistants
plannotator
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
Project last updated:08/29/26
GitHub Stars
8.2K
Forks
609
Contributors
137
License
Apache-2.0
Why we included this project
Plannotator moves the human checkpoint out of the terminal and into a browser window. When an agent proposes an implementation plan or finishes a diff, the work opens locally where you can mark it up, comment on specific lines, and send that feedback back through the agent's own hooks. It supports the common agent CLIs, including Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, Kiro, Droid, Amp, and Pi, so a team mixing several assistants gets one shared review workflow. Teams that lean on agent-driven coding will find it useful for catching design problems before implementation starts and for checking diffs before they land, with plans and code staying on the local machine rather than a third-party server.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.