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/waynesutton/promptstack/helpgit clone --depth 1 https://github.com/waynesutton/promptstackWhat 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 | $0.00000 | $0.00499 |
| Opus 5 | $0.00000 | $0.00249 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
help 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.
What it actually says
description: full-stack AI convex developer globs: alwaysApply: false
- Reflect Deeply Before Acting • Carefully reflect on why the current implementation or response may not be working. • Identify what’s missing, incomplete, or incorrect based on the original request. • Theorize different possible sources of the problem or areas requiring updates. • Then distill your reasoning down to the 1–2 most probable root causes or solutions. Only proceed after clear understanding.
⸻
- When Implementing Solutions
Follow Convex’s recommended approaches at all times: • Use direct mutation calls with plain objects. • Create dedicated mutation functions that map form fields directly to database fields. • Ensure form field names exactly match the corresponding database field names when applicable.
Use Convex documentation:
• Mutation Functions: https://docs.convex.dev/functions/mutation-functions
• Actions: https://docs.convex.dev/functions/actions
• Query Functions: https://docs.convex.dev/functions/query-functions
• Argument and Return Value Validation: https://docs.convex.dev/functions/validation
• General Function Docs: https://docs.convex.dev/functions
Understand the following foundational principles: • Zen of Convex: https://docs.convex.dev/understanding/zen • End-to-End Type Support with TypeScript: https://docs.convex.dev/understanding/best-practices/typescript • Convex Best Practices: https://docs.convex.dev/understanding/best-practices/ • Convex Schema Validation: https://docs.convex.dev/database/schemas
⸻
- Change Scope and Restrictions • Update Convex Schema if needed • Only update files when it’s directly necessary to fix the original request. • Do not change any UI, layout, design, or color styles unless specifically instructed. • Preserve all current admin dashboard sections and frontend components unless explicitly told to update, fix, or replace them. • Never remove sections, features, or components unless directly requested.
⸻
- Don’t write any code until you’re very confident (95% or more) in what needs to be done.
If unclear, ask for more info.
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 · 56 lines · 0 tokens per session scan A 99db64184e4b
help is a cursor rule published in the GitHub repository waynesutton/promptstack (76 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 499 tokens. 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
README
Professional README Standards for GitHub OSS Projects - Design, Structure, and Best Practices.
Documentation
Professional Documentation Standards for GitHub OSS Projects - Developer, Collaborator, and User Readiness.
audit
Code Audit Practices and Security Assessment Standards.
backend
Backend Development Practices and API Design Standards.
ci
CI/CD Pipeline Practices and DevOps Automation Standards.
finetune
AI Model Fine-Tuning Practices and Machine Learning Standards.