How do I install the Dual Agent Debate skill?

Run npx skillmds@latest add dvcrn/dual-agent-debate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dual Agent Debate safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dual Agent Debate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dual Agent Debate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Dual Agent Debate?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dual Agent Debate by dvcrn — Agent Skill

Name: Dual Agent Debate
Rating: 4.2 (5 reviews)
Author: dvcrn

Dual Agent Debate

Run a structured 2-agent debate loop between ChatGPT (OpenAI API) and the user's own thoughts retrieved from Supabase Open Brain via MCP, iterating up to 3 rounds (or until semantic agreement), then write the final outcome back to Open Brain. Use when user asks to compare/pressure-test an idea against prior thoughts or memory.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

DualAgentDebate

Execute scripts/dual_agent_debate.py to run the debate loop.

Setup

Set required environment variables:

export OPENBRAIN_MCP_URL="http://127.0.0.1:54321/mcp"
# optional if MCP is protected
export OPENBRAIN_MCP_TOKEN="..."

Optional: if you want direct OpenAI API mode, set:

export OPENAI_API_KEY="..."

If OPENAI_API_KEY is not set, the script uses openclaw agent (OAuth-backed local setup) for debate responses.

Optional tool/model overrides (defaults shown):

export OPENBRAIN_CONTEXT_TOOL="search_docs"
export OPENBRAIN_SQL_TOOL="execute_sql"
export DEBATE_MODEL="gpt-4o-mini"

Run

python3 skills/dual-agent-debate/scripts/dual_agent_debate.py \
  --query "Should I migrate this service to Supabase edge functions?"

Optional explicit thoughts:

python3 skills/dual-agent-debate/scripts/dual_agent_debate.py \
  --query "Should we launch this feature now?" \
  --thoughts "My concern is reliability and on-call burden." \
  --rounds 3 \
  --agreement-threshold 0.9

Behavior

Pull context from Open Brain MCP (OPENBRAIN_CONTEXT_TOOL).
Pull related prior thoughts from public.thoughts via MCP execute_sql unless --thoughts is provided.
Ask ChatGPT to debate the query using context and thoughts.
Compute semantic similarity (OpenAI embeddings) between ChatGPT reply and thoughts.
Repeat up to 3 rounds or stop early on agreement threshold.
Persist full outcome into public.memories via MCP execute_sql.

Notes

If your Open Brain MCP uses different tool names or argument schemas, set the tool env vars accordingly.
The script uses MCP tools/call JSON-RPC shape; point OPENBRAIN_MCP_URL at your MCP HTTP endpoint.

---name: dual-agent-debatedescription: Run a structured 2-agent debate loop between ChatGPT (OpenAI API) and the user's own thoughts retrieved from Supabase Open Brain via MCP, iterating up to 3 rounds (or until semantic agreement), then write the final outcome back to Open Brain. Use when user asks to compare/pressure-test an idea against prior thoughts or memory.---# DualAgentDebateExecute `scripts/dual_agent_debate.py` to run the debate loop.## SetupSet required environment variables:```bashexport OPENBRAIN_MCP_URL="http://127.0.0.1:54321/mcp"# optional if MCP is protectedexport OPENBRAIN_MCP_TOKEN="..."```Optional: if you want direct OpenAI API mode, set:```bashexport OPENAI_API_KEY="..."```If `OPENAI_API_KEY` is not set, the script uses `openclaw agent` (OAuth-backed local setup) for debate responses.Optional tool/model overrides (defaults shown):```bashexport OPENBRAIN_CONTEXT_TOOL="search_docs"export OPENBRAIN_SQL_TOOL="execute_sql"export DEBATE_MODEL="gpt-4o-mini"```## Run```bashpython3 skills/dual-agent-debate/scripts/dual_agent_debate.py \ --query "Should I migrate this service to Supabase edge functions?"```Optional explicit thoughts:```bashpython3 skills/dual-agent-debate/scripts/dual_agent_debate.py \ --query "Should we launch this feature now?" \ --thoughts "My concern is reliability and on-call burden." \ --rounds 3 \ --agreement-threshold 0.9```## Behavior1. Pull context from Open Brain MCP (`OPENBRAIN_CONTEXT_TOOL`).2. Pull related prior thoughts from `public.thoughts` via MCP `execute_sql` unless `--thoughts` is provided.3. Ask ChatGPT to debate the query using context and thoughts.4. Compute semantic similarity (OpenAI embeddings) between ChatGPT reply and thoughts.5. Repeat up to 3 rounds or stop early on agreement threshold.6. Persist full outcome into `public.memories` via MCP `execute_sql`.## Notes- If your Open Brain MCP uses different tool names or argument schemas, set the tool env vars accordingly.- The script uses MCP `tools/call` JSON-RPC shape; point `OPENBRAIN_MCP_URL` at your MCP HTTP endpoint.

Frequently asked questions