plan-mode

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

The tool for interactively reviewing an HTML plan for Claude Code

Systematic thinking enforcement plugin for OpenClaw — task tracking, plan mode, hard gates, quality checklists, and audit logging for AI agents

Kimi Code-style agent orchestration harness for the Pi coding agent — Swarm, Goal, Plan, Permission, Task, Hooks, Skills, TUI

Pi extension for plan mode - read-only exploration and analysis

Read-only plan mode for pi — structured planning, phased execution, and token optimization

Command Autopilot — use 100% of Claude Code while memorizing zero commands. Silent automation, right-moment suggestions with benefits, self-evolving to your habits.

让 Agent 的工作方式可组合、可审查、可持续改进，最终实现 Agent Self Evoling。 DeepSeek Harness Web plugin with composable task controls and isolated, human-reviewed self-evolution.

Don't go into production without these - 3 auto-triggering Claude Code skills for cost and drift prevention. 6 months of practitioner notes.

Plan safely, approve explicitly, then implement here or in a clean session.

One-click enter/exit Plan mode for the DSH web input bar, a quick-click shortcut for /plan

Sharable distillations of working-effectively-with-Claude-Code doctrines + tools (saga-21 corpus)

MendCode: Customizable CLI for agents, teams, memory, reviews, and TUI.

A living, executable showcase and practical toolkit for Grok Build (xAI). Includes reusable skills, exemplary AGENTS.md, a Grok-readiness auditor CLI, and demonstrations of Plan Mode + subagents.

A universal agent skill for structured plan mode. Built natively for OpenClaw and Claude Code. Works with Cursor, Windsurf, Codex CLI, Aider, and more.

Catch the bad plan before you spend the tokens. Cross-LLM peer review via MCP.

A terminal user interface (TUI) for reviewing and iterating on Claude's plans before implementation.

A Plan-Mode-first Codex skill for extracting project philosophy, anti-goals, and mental harnesses through guided dialogue.

Review and annotate Claude Code plan-mode plans in a VS Code panel, and send structured feedback back to the agent.