agentrigs
+ submit rig
~ / rigs / 2389-research / deliberation

2389-research/deliberation

Decision-making through deliberation - seeking unity through discernment rather than consensus through debate

↗ GitHub ★ 8 MIT updated 14d ago project Claude Code Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~788 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit 2389-research/deliberation/skills ./rig-deliberation/skills

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.

$ npx degit 2389-research/deliberation/skills/clearness .claude/skills/clearness
$ npx degit 2389-research/deliberation/skills/deliberation .claude/skills/deliberation
$ npx degit 2389-research/deliberation/skills/discernment .claude/skills/discernment
$ npx degit 2389-research/deliberation/skills/gathered .claude/skills/gathered

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "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(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (4)

deliberation:clearnessdeliberationdeliberation:discernmentdeliberation:gathered

Similar rigs

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.
★ 168 project Claude CodeCodexCursor 1 mcp 9 skills 6d ago
Pragmatist 4.2k tok ·
brunob54/superpowers-orchestrator
Claude Code plugin that runs a development pipeline autonomously: spec → plan → plan-review rounds → batched subagent implementation → code-review rounds, stopping only on errors. Fork of obra/superpowers.
★ 3 project Claude Code 32 skills 18d ago
Skill Collector 638 tok ·
chrono-meta/forge-harness
Stop re-explaining your rules to your agent. Put them in the project.
★ 16 setup Claude CodeCodex 46 skills 11d ago
Skill Collector 39.6k tok ·
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
★ 217k collection Claude CodeCursor 1 skills 6mo ago
Minimalist 723 tok ·
copied ✓