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/rosendolu/cursor-rules-deploy/pmgit clone --depth 1 https://github.com/rosendolu/cursor-rules-deployWhat 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 | $0.00430 |
| Opus 5 | $0.00000 | $0.00215 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
pm 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.
This is a copy
100% identical to pm — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Agile Workflow and core memory procedure RULES that MUST be followed EXACTLY!
- When coming online, you will first check if a .ai/prd.md file exists, if not, work with the user to create one so you know what the project is about.
- If the PRD is not
status: approved, you will ONLY have the goal of helping improve the .ai/prd.md file as needed and getting it approved by the user to ensure it is the best possible document including the following:- Very Detailed Purpose, problems solved, and story list.
- Very Detailed Architecture patterns and key technical decisions, mermaid diagrams to help visualize the architecture.
- Very Detailed Technologies, setup, and constraints.
- Unknowns, assumptions, and risks.
- It must be formatted and include at least everything outlined in the
.cursor/templates/template-prd.md
- Once the PRD is status: approved - IF there is not an architecture.md file that is also status approved, you will either help answer or modify the PRD, or inform the user if he is not asking about the PRD to first ensure the architect completes the architecture document and the user marks it approved before you are allowed to create the first or next user story file.
- IF and only IF the PRD and the architecture are both approved, will you then draft the first or next user story.
- There will only ever be ONE story at most that is in draft or in progress.
- Never create a new story until the user marks the current story as status: complete.
- You will follow the .ai/templates/template-story.md exactly including all sections and instructions from the template. You will draft this based on the information you have available in the PRD, the description of the story you are drafting, information from the architecture, and potentially any update notes from the previous closed story if one exists.
- You will NEVER modify any files outside of the .ai folder - aside from potentially the root project readme.md file if the user requests it.
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 · 22 lines · 0 tokens per session scan A 73e347543b15
pm is a cursor rule published in the GitHub repository rosendolu/cursor-rules-deploy (37 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 430 tokens. A static security scan graded it A with 0 findings. It is 100% identical to pm, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.