cursorrules

A multi-model discussion system for planning and analysis questions. It lets several AI models contribute responses through shared files, and requires Agent mode to run.

In plain words
What is it for?
Use it to deliberate about plans, designs, or analysis questions. Start a request with council: when the system is active; in Ask or Plan mode, switch to Agent mode first.
Why use it?
It helps compare different AI perspectives on a question instead of relying on one response. It also provides a shared place for those responses across coding workspaces.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/fiale-plus/cursor-council/cursorrules
Clone the repo
git clone --depth 1 https://github.com/fiale-plus/cursor-council

Made for: Cursor.

Per session 1,863 This file is loaded in full into every session.
When invoked 1,863 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01863 $0.01863
Opus 5 $0.00932 $0.00932
Sonnet 5 $0.00373 $0.00373
Haiku 4.5 $0.00186 $0.00186

Measured yesterday against content hash 536cdf7fa049, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules scanned grade A with 0 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursorrules · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Council Mode Protocol

A multi-model deliberation system for planning and analysis questions.

IMPORTANT: Agent Mode Required

Council mode requires Agent mode to function - it needs to write files to ~/.cursor-council/. Ask mode and Plan mode are read-only and cannot participate in council deliberations.

When user says council: in Ask/Plan mode, remind them to switch to Agent mode first.

IMPORTANT: Shared Location for Worktrees

Council files are stored in a fixed shared location so all models/worktrees can access them:

~/.cursor-council/           # Shared across all worktrees and sessions

Always use this absolute path: ~/.cursor-council/ (expand ~ to actual home directory)

This ensures models running in different git worktrees can still see each other's responses.

Activation

Council mode activates when:

  • User message starts with council:
  • File ~/.cursor-council/active.json exists and is not stale (< 1 hour old)

Identity

Identify yourself consistently:

  • Claude models → use filename claude.md
  • GPT-4/GPT-4o → use filename gpt4.md
  • Gemini → use filename gemini.md
  • Other → use filename other-{modelname}.md

File Structure

~/.cursor-council/
  active.json           # { "topic": "...", "id": "...", "created": "ISO8601", "phase": "collecting|critiquing|synthesizing" }
  responses/
    {model}.md          # Each model's initial response
  critiques/
    {model}.md          # Each model's review of others
  synthesis/
    {model}.md          # Each model's synthesis (can have multiple!)

Commands & Behavior

council: {question}

Start or join a council topic.

  1. Check if ~/.cursor-council/active.json exists

    • If YES and same topic: join existing council
    • If YES and different topic: warn user, ask to council: clear first
    • If NO: create ~/.cursor-council/ directory and active.json
  2. Create active.json:

{
  "topic": "{user's question}",
  "id": "{short-hash-or-timestamp}",
  "created": "{ISO8601 timestamp}",
  "phase": "collecting"
}

Read the full file on GitHub · 233 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.

  1. yesterday First seen · 233 lines · 1,863 tokens per session scan A 536cdf7fa049

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository fiale-plus/cursor-council (1 stars, last pushed 8mo ago), licensed MIT. It adds 1,863 tokens to every session, about $0.0093 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.