The creator kit: 139 Claude Code commands, 22 skills and 5 agents that carry their own DTD grammar, laws and trust boundary. Creators for prompts, skills, hooks, commands, subagents, plans, MCP server
Commands that carry their own grammar, and a doctor that reads it
123 Claude Code slash commands, 22 skills and 5 agents whose answer grammar, verdicts, laws and trust boundary are declared in a DTD inside each file; a guided NPX installer; the Adiutor, a Stop hook that checks every answer against the DOCTYPE that produced it; and the Commander-Adiutor, a monitor that hands every failed answer to the session as the ledger closes it
You are welcome here, whatever you came for. If you want sharper thinking commands in your Claude Code sessions, start with Install: one line, and rdc uninstall undoes every byte of it. If you came to check whether the numbers on this page are real, start with Verify and try to break them; that is the point of the page, not an offence against it. If "DTD" is a word you last saw in 2002, nothing here requires you to write one: the commands work as commands, and the grammar rides inside them.
Questions that begin "this is probably a dumb question" are the ones the documentation failed to answer. Ask them in Discussions and they will be treated as defects in this page.
A slash command is a prompt. A prompt says what an answer should contain, in prose, and prose drifts: the template at the bottom stops matching the steps in the middle, the verdict words multiply, and nothing ever reads the answer back. This repository fixes the shape of the answer once, in the oldest schema language there is, and then reads it back.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/Nova-Violet-Role--RoT-DtD-Commander.html)
Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.
Riztazz/claude-io-guardA Claude Code plugin that checks every file and shell call an AI agent makes, fixes what it safely can, and tells the agent how to fix the rest. Windows and macOS.
KernelLord/pickysteveSkill router and context picker for Claude Code, Cursor, and Aider. Auto-picks the right skill for every prompt, with prompt-injection filtering for MCP.
cuongnbms/mastering-claude-codeCẩm nang thực chiến Mastering Claude Code (tiếng Việt): 16 chương biên soạn từ tài liệu chính thức của Anthropic — CLI, workflows, MCP, subagents, skills, hooks, plugins, CI/CD & tối ưu context.
shitianfang/jev-useClaude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
Global-AI-Group-Inc/content-generation-skillsMira AI content generation skills: genre playbooks and prompting knowledge for AI agents that generate video and images through the Mira MCP server
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.