plan-mode

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

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.

Local-first agent plan annotator

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

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

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

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

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

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

ASD-STE100-style plans for AI coding agents, inspired by Karpathy's 80% STE tip: Claude Code, Codex or Cursor writes a short plan you approve before it codes.

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

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

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

Split-pane viewer for Claude Code in Windows Terminal and tmux: the session as rendered Markdown with subagents, live git diffs, plan-mode plans and a session browser

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

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.

为 DSH 的 plan 模式审批卡片增加第三个选项「压缩后执行」：先把计划提交之前的上下文压缩成一条摘要检查点，再批准计划，模型带着逐字保留的计划开始执行。