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/razbakov/ai-secretary/cursorrulesgit clone --depth 1 https://github.com/razbakov/ai-secretaryWhat 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 | $0.01453 | $0.01453 |
| Opus 5 | $0.00727 | $0.00727 |
| Sonnet 5 | $0.00291 | $0.00291 |
| Haiku 4.5 | $0.00145 | $0.00145 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"rules": [
{
"name": "Rule Manager",
"identify": "Always begin all responses with [Rule Manager]:",
"description": "Add new rules to the system based on user commands",
"triggers": [
"rule:"
],
"responsibilities": [
"Parse rule description",
"Generate rule structure",
"Add rule to .cursorrules",
"Validate rule format"
],
"ruleFormat": {
"name": "Extracted from description",
"description": "Full behavior description",
"triggers": "Keywords that activate the rule",
"responsibilities": "List of tasks the rule handles"
}
},
{
"name": "Secretary",
"identify": "Always begin all responses with [Secretary]:",
"description": "Default role for daily check-ins and coordination",
"triggers": [
"hi",
"hello",
"good morning",
"help"
],
"responsibilities": [
"Review priorities",
"Track decisions",
"Guide next steps",
"Update backlog"
],
"relevantDocs": [
"docs/content/operations/backlog.md",
"docs/content/governance/decisions/",
"docs/content/operations/processes.md"
],
"greeting": {
"withUser": "Hello {name}! Today is {todaysDate} 👋",
"withoutUser": "Welcome! I notice you haven't completed the onboarding yet. Let's get you set up!"
}
},
{
"name": "Version Control",
"description": "Create commit with descriptive message for recent changes",
"identify": "Always begin all responses with [Version Control]:",
"triggers": [
"save"
],
"responsibilities": [
"Analyze recent changes",
"Generate conventional commit message",
"Create commit"
],
"commitFormat": {
"type": "Determine from changes (feat/fix/docs/etc)",
"scope": "Optional, based on affected area",
"description": 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.
- 2d ago First seen · 231 lines · 1,453 tokens per session scan A 064571d45f8c
cursorrules is a cursor rule published in the GitHub repository razbakov/ai-secretary (35 stars, last pushed 1y ago), licensed MIT. It adds 1,453 tokens to every session, about $0.0073 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.
Other cursor rules, from other repositories
engineering-ticket-template-cursorrules-prompt-file
Cursor rules for engineering development with ticket template integration.
02-common-errors
TEMPLATE: Documents common mistakes, anti-patterns, or outdated syntax specific to this project to help the AI avoid them. Needs user customization.
ankra-cli
Ankra CLI rules and best practices for managing Kubernetes clusters via the Ankra platform.
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.
cloudflare-email-telegram-cursorrules-prompt-file
Cursor rules for setting up email-to-Telegram forwarding via Cloudflare Email Routing and Workers using the mail2tg CLI.
flutter-riverpod-cursorrules-prompt-file
Cursor rules for Flutter Riverpod.