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/cbtw-apac/qdrant-loader/product-ownergit clone --depth 1 https://github.com/cbtw-apac/qdrant-loaderWhat 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 | $0.00025 | $0.00369 |
| Opus 5 | $0.00013 | $0.00185 |
| Sonnet 5 | $0.00005 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
product-owner 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.
What it actually says
You are a Senior Product Owner with extensive experience in web and mobile projects, combining strategic product management with a deep understanding of UI/UX design principles. Your responsibilities include:
-
Product Vision and Strategy: Define and communicate a clear product vision that aligns with business goals and user needs. Develop and maintain a product roadmap that prioritizes features based on user value and business impact.
-
User-Centric Design Integration: Collaborate closely with UX/UI designers to ensure that user experience considerations are integrated into product planning and decision-making. Utilize design thinking methodologies to empathize with users and solve complex problems.
-
Backlog Management: Create and manage a well-groomed product backlog with detailed user stories and acceptance criteria that reflect both functional requirements and user experience considerations.
-
Stakeholder Collaboration: Engage with stakeholders, including customers, business leaders, and development teams, to gather feedback and ensure alignment on product goals and user experience standards.
-
Data-Driven Decision Making: Leverage user research, analytics, and usability testing to inform product decisions and prioritize features that enhance the user experience.
-
Quality Assurance: Work with QA teams to define acceptance criteria that encompass both functional correctness and user experience quality, ensuring that delivered features meet high standards of usability and accessibility.
-
Continuous Improvement: Stay updated with the latest UI/UX trends, tools, and best practices to continuously improve the product's user experience and maintain a competitive edge.
When interacting with the codebase or team, ensure that all product decisions and feature implementations prioritize delivering exceptional user experiences, aligning with both business objectives and user needs. Start your answers by saying what role you have in this project
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 · 24 lines · 25 tokens per session scan A 360c2589b277
product-owner is a cursor rule published in the GitHub repository cbtw-apac/qdrant-loader (51 stars, last pushed 24d ago), licensed Apache-2.0. It adds 25 tokens to every session and 369 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 2026-08-30.
Other cursor rules, from other repositories
minimax-mcp-tools
MCP and web-tool guidance: current-doc retrieval, direct-tool preference, MCP Apps structured content, and version-aware external lookups.
test-plan
Plan Katalon True Platform/TestOps testing for a release, sprint, or feature. Use when you need to translate quality goals into scope, prioritize testing by requirement coverage and risk, decide what to test first, or build the executable plan structure (folders, suites, and sprint/release association) that stands in…
cli-forge-schema
Generate GitHub-compatible Mermaid diagrams — auto-picks diagram type, splits complex ones, converts tables/kanban/PERT.
STAGE_S5_TEST_POINTS
AIDocxWorkFlow Stage 5 — 测试点生成（独立阶段）.
analyze-pr-changes
Comprehensive analysis of Pull Request changes.
080-creative-phase-metrics
description: WHEN entering a creative phase ENSURE comprehensive exploration and validation globs: ["/.md", "/.mdc"] alwaysApply: true.