cursor

cursor is a cursor rule for coding agents from berkcangumusisik/agent-hub. It costs 243 tokens per session, scanned A, original, MIT.

Project rules for using agent-hub, a team-style setup in which an agent takes on roles such as architect, developer, tester, and security reviewer. It requires checking the project's profile and architecture decisions first.

In plain words
What is it for?
Use it when onboarding to the project, organizing specialist roles, reviewing work, making an architectural decision, or handing work to another role.
Why use it?
It keeps work aligned with the project's technology choices, conventions, and recorded decisions instead of relying on generic assumptions.

Cursor rule

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/berkcangumusisik/agent-hub/cursor
Clone the repo
git clone --depth 1 https://github.com/berkcangumusisik/agent-hub

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 cursor

README.md
[![agentmods](https://agentmods.dev/badge/rules/berkcangumusisik/agent-hub/cursor.svg)](https://agentmods.dev/rules/berkcangumusisik/agent-hub/cursor)
Your own site
<a href="https://agentmods.dev/rules/berkcangumusisik/agent-hub/cursor"><img src="https://agentmods.dev/badge/rules/berkcangumusisik/agent-hub/cursor.svg" alt="Measured on agentmods" height="20"></a>
Per session 243 This file is loaded in full into every session.
When invoked 243 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 $0.00243 $0.00243
Opus 5 $0.00121 $0.00121
Sonnet 5 $0.00049 $0.00049
Haiku 4.5 $0.00024 $0.00024

Measured 3d ago against content hash 116989811b36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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.

adapters/cursor.mdc · 26 lines

What it actually says

agent-hub

This project uses agent-hub: a project-aware specialist team. Operate as the team.

Profile-first protocol

  • Read .claude/agent-hub/profile.yml (stack, commands, conventions, active team). If missing, detect the stack and create it.
  • Read and honor any ADRs under .claude/agent-hub/decisions/.
  • Work in the project's real stack and conventions — never assume.

Operate as a team

Act as the tech-lead first: decompose the request, then handle each part as the right specialist — architect, backend/frontend/mobile/devops/data engineer, ux-designer, code-reviewer, qa-tester, security-reviewer, tech-writer. Self-review (correctness + security) and run the project's tests before finishing.

Commands

onboard · team · review · decide: <X> · handoff

Learn more: https://github.com/berkcangumusisik/agent-hub

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 · 26 lines · 243 tokens per session scan A 116989811b36

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository berkcangumusisik/agent-hub (14 stars, last pushed 2mo ago), licensed MIT. It adds 243 tokens to every session, about $0.0012 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 2026-08-30.