What is the-ai-counsel AGENTS.md?

Project instructions for an AI Counsel application where several language models answer a question, review one another, and produce a combined answer.

It helps run the backend and frontend, understand the deliberation stages, and work with supported model providers and the built-in service.

It gives coding agents the project structure, startup commands, ports, and service details they need to work safely in the repository.

How jacob-bd/the-ai-counsel configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to jacob-bd/the-ai-counsel. 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/jacob-bd/the-ai-counsel/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/jacob-bd/the-ai-counsel

Made for: Codex, OpenCode.

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/jacob-bd/the-ai-counsel/agents-md/github.svg)](https://agentmods.dev/instructions/jacob-bd/the-ai-counsel/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jacob-bd/the-ai-counsel/agents-md"><img src="https://agentmods.dev/badge/instructions/jacob-bd/the-ai-counsel/agents-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/jacob-bd/the-ai-counsel/agents-md"><img src="https://agentmods.dev/badge/instructions/jacob-bd/the-ai-counsel/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,046 This file is loaded in full into every session.

When invoked 6,046 The same file — it is already loaded in full.

Security scan C 2 findings. 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	$0.06046	$0.06046
Opus 5	$0.03023	$0.03023
Sonnet 5	$0.01209	$0.01209
Haiku 4.5	$0.00605	$0.00605

Measured 5d ago against content hash c2f3765c0745, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

the-ai-counsel AGENTS.md scanned grade C with 2 findings 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 5d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf frontend/node_modules && npm install --prefix frontend

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:11434/api/tags

AGENTS.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

Project Overview

The AI Counsel is a 3-stage deliberation system where multiple LLMs collaboratively answer user questions through:

Stage 1: Individual model responses (with optional web search context)
Stage 2: Anonymous peer review/ranking to prevent bias
Stage 3: Chairman synthesis of collective wisdom

Key Innovation: Hybrid architecture supporting OpenRouter (cloud), Ollama (local), Groq (fast inference), direct provider connections, and custom OpenAI-compatible endpoints.

Running the Application

Quick Start:

./start.sh

Manual Start:

# Backend (from project root)
uv run python -m backend.main

# Frontend (in new terminal)
cd frontend
npm run dev

Ports:

Backend: http://localhost:8001 (NOT 8000 - avoid conflicts)
Frontend: http://localhost:5173
MCP Server (SSE): Built-in at /mcp on the backend (http://localhost:8001/mcp/sse) — 10 action-based tools (council_deliberate, model_chat, advisor_debate, run_iterative_debate, council_settings, advisor_settings, personas, conversations, providers, config_backup). See docs/mcp/TOOLS.md. GET /api/health reports "mcp": {"tools": 10}.

Network Access:

# Backend with network access:
LLM_COUNCIL_BIND_HOST=0.0.0.0 uv run python -m backend.main

# Frontend with network access:
cd frontend && npm run dev -- --host

Backend bind variables:

LLM_COUNCIL_BIND_HOST: dev launcher bind host, default 127.0.0.1. Use 0.0.0.0 only when you intentionally want LAN access.
LLM_COUNCIL_BIND_PORT: dev launcher bind port, default 8001.
LLM_COUNCIL_ADMIN_TOKEN: required for remote access to /api/settings/export, /api/settings/import, and /api/settings/reset. Without it, those admin endpoints only accept direct loopback clients and reject proxied external clients.

Read the full file on GitHub · 424 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.

5d ago Changed · +2 lines · +103 tokens per session c2f3765c0745
9d ago First seen · 422 lines · 5,943 tokens per session scan C f57243dd5020

Subscribe to this mod's changes

the-ai-counsel AGENTS.md is an instructions file published in the GitHub repository jacob-bd/the-ai-counsel (111 stars, last pushed 4d ago), licensed MIT. It adds 6,046 tokens to every session, about $0.0302 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

the-ai-counsel: Instructions file for Codex