antonbabenko/deliberation
Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add deliberation -- npx -y @antonbabenko/deliberation-mcp $ npx degit antonbabenko/deliberation/.claude ./rig-deliberation # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add deliberation -- npx -y @antonbabenko/deliberation-mcp $ npx degit antonbabenko/deliberation/.agents/skills/architect .claude/skills/architect $ npx degit antonbabenko/deliberation/.agents/skills/code-reviewer .claude/skills/code-reviewer $ npx degit antonbabenko/deliberation/.agents/skills/debugger .claude/skills/debugger $ npx degit antonbabenko/deliberation/.agents/skills/deliberation .claude/skills/deliberation $ npx degit antonbabenko/deliberation/.agents/skills/plan-reviewer .claude/skills/plan-reviewer $ npx degit antonbabenko/deliberation/.agents/skills/reload-mcp .claude/skills/reload-mcp $ npx degit antonbabenko/deliberation/.agents/skills/researcher .claude/skills/researcher $ npx degit antonbabenko/deliberation/.agents/skills/scope-analyst .claude/skills/scope-analyst $ npx degit antonbabenko/deliberation/.agents/skills/security-analyst .claude/skills/security-analyst
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| @antonbabenko/deliberation-mcp · "deliberation" | npm | 2.5k |
Skills (9)
architectcode-reviewerdebuggerdeliberationplan-reviewerreload-mcpresearcherscope-analystsecurity-analyst
Cursor rules (1)
deliberation · always
Similar rigs
rcrdk/agent-kit
Cursor rules, agent commands, and bundled skills — one submodule for consistent AI coding across rcrdk projects Agent config for rcrdk: .mdc rules, slash commands, Karpathy skills, and DX bootstrap templates
Skill Collector 3.6k tok ·
krzysztofdudek/ResearcherSkill
One file. Your AI coding agent becomes a scientist. 30+ experiments while you sleep.
Minimalist 1.2k tok ·
Bastioned-successor320/learn-nanobot
Learn Nanobot with a beginner-friendly guide to AI Agent basics, interview prep, and core concepts for job seekers
Minimalist 240 tok ·
Hainrixz/the-architect
A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every bui
Pragmatist 3.0k tok ·