What is debate-hall-mcp CLAUDE.md?

An MCP server that runs structured debates between several AI models, using different viewpoints before producing a combined answer.

Brainstorming, weighing alternatives, pressure-testing plans, comparing approaches, and producing a synthesized decision.

It helps examine a question from opposing angles, surface objections, compare options, and reduce the chance of accepting the first idea.

How elevanaltd/debate-hall-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to elevanaltd/debate-hall-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/elevanaltd/debate-hall-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/elevanaltd/debate-hall-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/elevanaltd/debate-hall-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/elevanaltd/debate-hall-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/elevanaltd/debate-hall-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/elevanaltd/debate-hall-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/elevanaltd/debate-hall-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/elevanaltd/debate-hall-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 821 This file is loaded in full into every session.

When invoked 821 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00821	$0.00821
Opus 5	$0.00411	$0.00411
Sonnet 5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 8d ago against content hash 81d06c5e7486, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

debate-hall-mcp CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`chmod 600`), or `cp .env.example .env` and edit. The `.env` is gitignored;

CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in this repo with Claude Code

This repository is the Debate Hall MCP server: it can run an automated multi-model "Wind / Wall / Door" debate to think through a problem from three angles and hand back a synthesised answer.

Tool routing — read this first

When the user asks to debate, brainstorm, weigh options, compare approaches, pressure-test an idea, or find the best/"genius" solution to something, use the run_debate MCP tool. That is the front door.

Default to tier="standard" (three different frontier models debating).
Use tier="fast" only if the user asks for something quick, cheap, or low-stakes.
Pass the user's question as topic. Let everything else default — do not set mode="raci", compression_tier, primer_tier, or raci_config unless the user explicitly asks for that kind of control.
After it returns, present the synthesis (the Door's resolution) clearly, then briefly summarise the strongest Wind ideas and Wall objections that shaped it.

Do not reach for the lower-level or alternative tools — init_debate / add_turn / get_debate / close_debate, pick_next_speaker, resolve_question, extract_decision_record, search_decisions, or the advisory/committee tools — unless the user explicitly asks for manual turn-by-turn control, a verified decision record, or one of those specific workflows. For everyday "let's think this through" requests, run_debate is always the right call.

There is also a /debate <your question> slash command that does exactly this.

Setup (one time)

Debate Hall is configured user-global, so run_debate is available from any project directory — you launch claude from whatever repo you want to think about, not from debate-hall-mcp. Clone the repo, then run the remaining commands from inside it:

git clone https://github.com/elevanaltd/debate-hall-mcp.git
cd debate-hall-mcp
pip install -e .                      # editable install from this clone
./setup-mcp.sh --claude-code          # run once (offers to store your API key)

Read the full file on GitHub · 66 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 66 lines · 821 tokens per session scan B 81d06c5e7486

Subscribe to this mod's changes

debate-hall-mcp CLAUDE.md is an instructions file published in the GitHub repository elevanaltd/debate-hall-mcp (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 821 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

debate-hall-mcp: Instructions file for Claude Code