cursorrules

cursorrules is a cursor rule for Cursor from AiraAlfredSF/project-brain-mcp. It costs 880 tokens per session, scanned A, original, MIT.

A project rule set for working with the code-brain MCP server, a service that stores project decisions and maps code dependencies. MCP is a standard way for an AI agent to call external tools.

In plain words
What is it for?
It is for starting compliant sessions, retrieving decisions and constraints, validating plans, and recording important architectural choices.
Why use it?
It gives each coding session shared project context, recorded constraints, and checks that plans follow the repository's rules.

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/airaalfredsf/project-brain-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/AiraAlfredSF/project-brain-mcp

Made for: Cursor.

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.

agentmods badge for cursorrules

README.md
[![agentmods](https://agentmods.dev/badge/rules/airaalfredsf/project-brain-mcp/cursorrules.svg)](https://agentmods.dev/rules/airaalfredsf/project-brain-mcp/cursorrules)
Your own site
<a href="https://agentmods.dev/rules/airaalfredsf/project-brain-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/airaalfredsf/project-brain-mcp/cursorrules.svg" alt="Measured on agentmods" height="20"></a>
Per session 880 This file is loaded in full into every session.
When invoked 880 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 $0.00880 $0.00880
Opus 5 $0.00440 $0.00440
Sonnet 5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 3d ago against content hash 7b6ed8b1d619, 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 3d 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.

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.

skills/cursor/.cursorrules · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-brain-mcp — Checklist

This project runs the code-brain MCP server, giving you persistent decision memory, a codebase dependency graph, plan validation, and a self-bootstrapping constraints file. Work through this checklist as you go.

Session lifecycle

  • Call start_session() at the start of every session. Resets compliance tracking and (on the first call of the process) prints the BRAIN DSL v1 schema header needed to interpret every other tool's output.
  • Periodically call get_session_health() (roughly every 10 turns). If it returns SESSION: warnings or SESSION: violations, follow the action: line(s) before continuing.
  • Do not call record_tool_call yourself — the server invokes it automatically after every tool call.

Decision memory (Spec 01)

  • Before starting any task, call get_context(topic) for the task's topic.
  • Call list_constraints() to review architectural and technology constraints before making changes that might touch them.
  • After making an architectural decision (library, pattern, data model, API shape, etc.), call log_decision(decision, rationale, alternatives_rejected, tags).
  • When an approach fails, call log_failure(description, cause, approach_tried) before trying an alternative.

Codebase graph (Spec 02)

  • After first setup, or whenever the code graph seems stale, call index_codebase() to (re)build the dependency graph.
  • Before modifying a module, call get_dependents(module) to see what depends on it.
  • Before changing a module, call get_dependencies(module) to understand what it relies on.
  • Before a significant or risky change, call get_blast_radius(module) for the full transitive impact.
  • After pulling new commits, call diff_graph(since_commit) to see structural changes since the last index.
  • When starting a task described at a high level, call find_entry_points(intent) to locate the relevant module(s).

Read the full file on GitHub · 81 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. 3d ago First seen · 81 lines · 880 tokens per session scan A 7b6ed8b1d619

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository AiraAlfredSF/project-brain-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 880 tokens to every session, about $0.0044 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.