Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/waynesutton/promptstacknpx agentmods add rules/waynesutton/promptstack/cursorrulesWrote 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/waynesutton/promptstack/cursorrules)<a href="https://agentmods.dev/rules/waynesutton/promptstack/cursorrules"><img src="https://agentmods.dev/badge/rules/waynesutton/promptstack/cursorrules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/waynesutton/promptstack/cursorrules"><img src="https://agentmods.dev/badge/rules/waynesutton/promptstack/cursorrules.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02013 | $0.02013 |
| Opus 5.5 | $0.00805 | $0.00805 |
| Sonnet 5.5 | $0.00403 | $0.00403 |
| Haiku 4.5 | $0.00201 | $0.00201 |
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 1mo 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This document serves as some special instructions when working with Convex.
best practices
https://docs.convex.dev/understanding/best-practices/
dev workflow
https://docs.convex.dev/understanding/workflow
#typescript https://docs.convex.dev/understanding/best-practices/typescript
Schemas
When designing the schema please see this page on built in System fields and data types available: https://docs.convex.dev/database/types
also use Standard Schema https://github.com/standard-schema/standard-schema
Here are some specifics that are often mishandled:
validator (https://docs.convex.dev/api/modules/values#v)
The validator builder.
This builder allows you to build validators for Convex values.
Validators can be used in schema definitions and as input validators for Convex functions.
Type declaration
Name Type
id (tableName: TableName) => VId<GenericId, "required">
null () => VNull<null, "required">
number () => VFloat64<number, "required">
float64 () => VFloat64<number, "required">
bigint () => VInt64<bigint, "required">
int64 () => VInt64<bigint, "required">
boolean () => VBoolean<boolean, "required">
string () => VString<string, "required">
bytes () => VBytes<ArrayBuffer, "required">
literal (literal: T) => VLiteral<T, "required">
array (element: T) => VArray<T["type"][], T, "required">
object (fields: T) => VObject<Expand<{ [Property in string | number | symbol]?: Exclude<Infer<T[Property]>, undefined> } & { [Property in string | number | symbol]: Infer<T[Property]> }>, T, "required", { [Property in string | number | symbol]: Property | ${Property & string}.${T[Property]["fieldPaths"]} }[keyof T] & string>
record <Key, Value>(keys: Key, values: Value) => VRecord<Record<Infer, Value["type"]>, Key, Value, "required", string>
union (...members: T) => VUnion<T[number]["type"], T, "required", T[number]["fieldPaths"]>
any () => VAny<any, "required", string>
optional (value: T) => VOptional
System fields (https://docs.convex.dev/database/types#system-fields)
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.
- 1mo ago First seen · 201 lines · 2,013 tokens per session scan A f56486d7eeb5
cursorrules is a cursor rule published in the GitHub repository waynesutton/promptstack (78 stars, last pushed 1y ago), licensed MIT. It adds 2,013 tokens to every session, about $0.0081 per session on Opus 5.5. 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
supabase
Do not use the Supabase Client, instead use the Jawn Client and put all new endpoints in controllers. Don't use RLS policies, instead enable RLS for new tables and revoke privledges. Example.
jawn
Cursor rule "jawn" from Helicone/helicone, covering helicone jawn controller and tanstack query integration, controller pattern, manager pattern, frontend hooks with tanstack query and type definitions.
rulesforconvex
description: Convex guidelines globs: alwaysApply: true.
startup-migration-bounded-work
Production djangostartup migrate must be bounded; never run makemigrations in production.
redis_rate_limiting
Complete guide for implementing Redis-based rate limiting with authentication troubleshooting and FastAPI integration.
schema
Scalable and secure schema design patterns for relational databases, NoSQL, and APIs. / TR: İlişkisel veri tabanları, NoSQL ve API'ler için ölçeklenebilir ve güvenli şema tasarım kalıpları.