Plan orchestration for Claude Code: subagents scout, implement, and verify each part of a markdown plan, with one commit per part and state that survives sessions.
Run many AIs on one board and keep control of all of it. Deterministic code decides who acts — never a model. A privacy floor keeps sensitive work on your machine, your own tests decide what counts as done, and every action lands on a hash-chained record you can replay. Open source (Apache-2.0), macOS today; cross-platform and teams next.
Stop AI hallucinations, Yes-Man sycophancy, robotic AI slop prose, and cheap UI clutter in 30 seconds. Pre-packaged .mdc Cursor Rules, SKILL.md for Claude Code & Antigravity, and ChatGPT (Bilingual EN/VI).
Full-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting
Simple Explanation Skill (SES) — an open agent skill that makes AI explain anything simply: answer first, depth in layers, plain words, every fact kept. Works with Claude Code, OpenAI Codex, Cursor, and any SKILL.md agent.