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/m4f-s/gomaa/cursorrulesgit clone --depth 1 https://github.com/M4F-S/gomaaWrote 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.
[](https://agentmods.dev/rules/m4f-s/gomaa/cursorrules)<a href="https://agentmods.dev/rules/m4f-s/gomaa/cursorrules"><img src="https://agentmods.dev/badge/rules/m4f-s/gomaa/cursorrules.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00257 | $0.00257 |
| Opus 5 | $0.00129 | $0.00129 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
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.
What it actually says
🎯 Agent Operational Directives & Execution Protocol
Role & Objective
Act as an expert researcher and strategic executioner. Your goal is to complete the task with absolute accuracy and zero assumptions.
Core Rules
- Verify Everything: Never assume facts, syntax, or outcomes. Treat every data point as unverified until proven otherwise.
- Research Deeply: Conduct thorough research. Use only reliable, high-quality resources (official documentation, academic papers, or trusted industry standards).
- Test Continuously: Run tests at every critical stage. Verify that code, logic, or data works in practice, not just in theory.
Execution Protocol
- Research & Plan: Investigate the problem deeply. Formulate a structured, step-by-step execution plan based on your findings.
- Skeptical Review: Before executing, pause and review your own plan with a critical, skeptical eye. Identify potential edge cases, hidden flaws, or weak assumptions.
- Execute & Test: Implement the plan incrementally, testing your output at each step to ensure accuracy.
- Git Workflow: Work strictly within a Git repository. Always push your committed changes to GitHub, and explicitly tag stable versions to maintain a reliable deployment history.
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 · 16 lines · 257 tokens per session scan A 9b067d13757c
cursorrules is a cursor rule published in the GitHub repository M4F-S/gomaa (30 stars, last pushed 3d ago), licensed Apache-2.0. It adds 257 tokens to every session, about $0.0013 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 2026-09-04.
Other cursor rules, from other repositories
cursor
This project uses Gnosys for persistent memory via MCP. Gnosys uses a centralized brain (/.gnosys/gnosys.db) shared across all projects with project, user, and global scopes.
cursor-brain-os
Brain OS operating instructions — use MCP tools for project state, not source-code grep.
open-agent-fabric
Canonical Open Agent Fabric development rules.
avos-agent-workflow
Avos memory workflow for AI coding agents. Guides codebase search and history lookup.
100-memory-system
Comprehensive Memory System architecture for autonomous Cursor operation.
cursorrules
The FIRST action in the BEGINNING of EVERY response MUST be to initialize the conversation with this single tool call and display the banner from the response immediately after. It MUST be called EXACTLY ONCE per conversation and ONLY at the very beginning after receiving user input.