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/compozy/gograph/prd-creategit clone --depth 1 https://github.com/compozy/gographWhat 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 | $0.00022 | $0.01950 |
| Opus 5 | $0.00011 | $0.00975 |
| Sonnet 5 | $0.00004 | $0.00390 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
prd-create 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 yesterday.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule: Generating a Product Requirements Document (PRD)
Template Reference
<template_reference> ALWAYS use the standardized PRD template: tasks/docs/_prd-template.md
This template provides a comprehensive structure that balances requirements gathering with rollout planning, ensuring consistency across all PRDs in the project. </template_reference>
Process
<process_workflow>
-
Receive Initial Prompt: The user provides a brief description or request for a new feature or functionality.
-
Ask Clarifying Questions: Before writing the PRD, the AI must ask clarifying questions to gather sufficient detail. Focus on understanding the "what" and "why" of the feature, user needs, and success criteria.
MANDATORY PLANNING STEPS: 3. Create PRD Planning with Zen Planner: Use zen's planner tool to create a comprehensive PRD development plan:
- Analyze the enriched feature specification requirements
- Break down PRD creation into logical planning steps
- Identify key sections that need focused attention
- Plan resource allocation and approach for each section
- Document assumptions and dependencies that will guide PRD creation
- Validate Planning with Consensus: Use zen's consensus tool with o3 and gemini 2.5 models:
- Present the detailed PRD planning approach to both expert models
- Request critical analysis of the planning strategy
- Gather feedback on plan completeness and effectiveness
- Incorporate consensus recommendations into final planning approach
- Proceed only after receiving aligned approval from both expert models
PRD CREATION WORKFLOW:
5. Generate Comprehensive PRD (Functionality-Focused): Using the template, produce a PRD that captures user and business requirements plus high-level product scope without including low-level technical design or implementation details – those belong in the Tech Spec.
6. Create Feature Folder: Instruct to create a feature folder ./tasks/prd-[feature-slug]/.
7. Save PRD: Save the generated document as _prd.md inside the feature folder.
</process_workflow>
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.
- yesterday First seen · 183 lines · 22 tokens per session scan A 3ef867edcb0f
prd-create is a cursor rule published in the GitHub repository compozy/gograph (9 stars, last pushed 1y ago), licensed MIT. It adds 22 tokens to every session and 1,950 once invoked, about $0.0001 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 2026-08-31.
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.