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.
npx agentmods add rules/fiale-plus/cursor-council/cursorrulesgit clone --depth 1 https://github.com/fiale-plus/cursor-councilWhat 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 | $0.01863 | $0.01863 |
| Opus 5 | $0.00932 | $0.00932 |
| Sonnet 5 | $0.00373 | $0.00373 |
| Haiku 4.5 | $0.00186 | $0.00186 |
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.
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.jsonexists 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.
-
Check if
~/.cursor-council/active.jsonexists- If YES and same topic: join existing council
- If YES and different topic: warn user, ask to
council: clearfirst - If NO: create
~/.cursor-council/directory andactive.json
-
Create
active.json:
{
"topic": "{user's question}",
"id": "{short-hash-or-timestamp}",
"created": "{ISO8601 timestamp}",
"phase": "collecting"
}
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.
- yesterday First seen · 233 lines · 1,863 tokens per session scan A 536cdf7fa049
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.
Other cursor rules, from other repositories
component-development
Modern React + TypeScript component patterns — hooks, typed props, performance optimization, forms, and testing.
webdriver-management
Selenium WebDriver lifecycle management — driver factory, explicit waits, browser options, and teardown.
api-testing
Cypress network interception and API testing patterns (cy.intercept, service mocking, request/response validation).
app-router-patterns
Next.js 14+ App Router patterns — Server Components, Client Components, Route Handlers, Server Actions, and metadata API.
page-object-patterns
Page Object Model patterns for Selenium — BasePage, component objects, and fluent interfaces.
test-patterns
Selenium pytest test patterns — data-driven tests, fixtures, error handling, and performance checks.