Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
-
Updated
May 13, 2026 - TypeScript
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
Local-first agent plan annotator
Systematic thinking enforcement plugin for OpenClaw — task tracking, plan mode, hard gates, quality checklists, and audit logging for AI agents
Pi extension for plan mode - read-only exploration and analysis
Don't go into production without these - 3 auto-triggering Claude Code skills for cost and drift prevention. 6 months of practitioner notes.
Sharable distillations of working-effectively-with-Claude-Code doctrines + tools (saga-21 corpus)
A Plan-Mode-first Codex skill for extracting project philosophy, anti-goals, and mental harnesses through guided dialogue.
A universal agent skill for structured plan mode. Built natively for OpenClaw and Claude Code. Works with Cursor, Windsurf, Codex CLI, Aider, and more.
Treat your Claude Code plans like database migrations. Auto-capture plan mode into immutable repo history.
OpenClaw skill: PLAN mode - BUILD mode with auto-debug, auto-test, and Plan Fidelity Score.
Real-time plan-drift watchdog for Claude Code. Keeps Claude honest to its own plan.
Force 5 LLMs (Haiku 4.5 + Sonnet 4.6 + Opus + 3 local Ollama) to peer-review every Claude Code plan. Hook-gated. No bypass. Fully local for the open-weight reviewers.
V2.1 Alpha — multi-model agent framework with five-layer working memory, plan-mode orchestration, and real quality control.
🛠 Review TypeScript and React code with precise, actionable feedback like a senior engineer for better code quality and faster development.
Add a description, image, and links to the plan-mode topic page so that developers can more easily learn about it.
To associate your repository with the plan-mode topic, visit your repo's landing page and select "manage topics."