Use deliberation MCP experts for review and second opinions.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
The deliberation MCP server gives you GPT, Gemini, Grok, and OpenRouter as
expert subagents. Call its tools when a task warrants outside input:
- Plan or architecture review: call `consensus` or the `architect` /
`plan-reviewer` tool.
- Security review of auth, untrusted input, or a new endpoint: call
`security-analyst`.
- A second opinion, or after a fix has failed twice: call `ask-all` or a single
`ask-gpt` / `ask-gemini` / `ask-grok` tool.
Pass full context in the `prompt` - the experts do not share your session.
Read the result, then apply your own judgment. Skip delegation for simple edits
and first-attempt fixes.
The line at the top of this page pins the label git:20260601.52dd6fe, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_nk4rs6qmji5acnx4
GET https://markdownregistry.com/api/v1/resolve?ref=antonbabenko/deliberation/.cursor/rules/deliberation.mdc
GET https://markdownregistry.com/api/v1/blob/c07f257a1c3b89ac14a4b52f9bed4915819558646229330df345282e3578c641
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
antonbabenko/deliberation · .agents/skills/deliberation/SKILL.md · When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
antonbabenko/deliberation · .agents/skills/writing-editor/SKILL.md · Edit prose so it reads like its author wrote it, keeping every fact and the author's voice.
antonbabenko/deliberation · plugins/deliberation/skills/deliberation/SKILL.md · When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
antonbabenko/deliberation · .gemini/skills/deliberation/SKILL.md · When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
antonbabenko/deliberation · .agents/skills/deliberation/SKILL.md · When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
brunob54/superpowers-orchestrator · skills/deliberation/SKILL.md · Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not…