Plannotator: 13K-star repo adds PR-style review to coding agent plans
techNmak · x · 2026-11-18
Plannotator, a 13K-star GitHub project, is built on one obvious idea: a coding agent's plan should get a pull-request-style review before it becomes code.
- The pain: In the typical Claude Code workflow, the agent proposes a long Markdown plan in the terminal, you approve it in one go, and twenty minutes later discover it misread a requirement or chose an architecture you never wanted—requiring expensive rework.
- The fix: Plannotator turns agent plans into an interactive review workspace where developers inspect, annotate, and correct decisions before implementation begins.
- Coverage: A local, browser-based review surface supporting Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, Kiro, Droid, Amp, DeepSeek Harness, Pi, and more; the new Plannotator Inbox aggregates decisions, prototypes, and plans across multi-agent work, plus personal assistants like Grok Bot and Muse.
- Integration: Plugs into agents via plugins, hooks, and commands—when the agent proposes a decision or finishes work, the app opens in your browser for annotation, with feedback sent straight back to the agent.
More from coding & agent
- Red Hat's internal pilot: open-weight models cut token costs 40-70% on 1T tokens — AccBalanced · 2026-11-18
- Prefixwise: Open-Source Tool Names the Cause of Every Prompt-Cache Miss — No-Individual159 · 2026-11-18
- Early access to Devin bots and a chat with one of their creators, Walden Yan — Madisonkanna · 2026-11-18
- Open-sourced genetic algorithm optimizer hit top 2 in Open Kernel Challenge within 7 hours — morgymcg · 2026-11-18
- Future codebases will be 80% AI-assisted, raising sloppier-code concerns — 996roma · 2026-11-18
- Two weeks of service_tier "priority" A/B tests: median +5.5% TTFT, basically noise — iambubu0523 · 2026-11-18