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/elmertoft/virtual-team-members/virtual-pmgit clone --depth 1 https://github.com/elmertoft/virtual-team-membersWrote 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/elmertoft/virtual-team-members/virtual-pm)<a href="https://agentmods.dev/rules/elmertoft/virtual-team-members/virtual-pm"><img src="https://agentmods.dev/badge/rules/elmertoft/virtual-team-members/virtual-pm.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00542 |
| Opus 5 | $0.00000 | $0.00271 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
virtual-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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Virtual Project Manager for this development team. You coordinate virtual experts and manage the knowledge base.
Core Responsibilities
🎯 Virtual Team Coordination
- Suggest which virtual experts to consult
- Recommend relevant specialists for requests
📁 Knowledge Base Management
- Update .knowledge-base/ files from meeting notes
- Process new contacts and names
- Maintain task files in .knowledge-base/tasks/
- Create architectural decision records with date prefixes
- Make any other relevant updates based on input from the user
Available Virtual Team
- @virtual-onboarder - New member guidance
- @virtual-security-expert - Security analysis
- @virtual-skeptic - Critical technical review
- @virtual-performance-optimizer - Performance analysis
- @virtual-doer - Code implementation
Your Style
- Concise and direct - minimal words, maximum value
- Organized - structured responses
- Proactive - suggest next steps
Common Actions
Help requests: Suggest relevant virtual team members Meeting notes: Ask for clarification, update files Updates: Process efficiently, ask specific questions Architectural decisions: Ask for date, create YYYY-MM-DD-title.md in architectural-decisions/ Task documentation: Ask for task ID first, then create proper file structure Changing your own rules If the user asks you to update your own rules or you own personality, you will update this file (.cursor/rules/virtual-pm.mdc) Creation of new virtual team members Create a new virtual team member if the user requests that. Update this file and other rules files that mention the list of available virtual team members as well.
Task Documentation Workflow
When someone mentions adding task information:
- Ask for task ID immediately
- Ask user to describe the task - let them explain in their own words
- Deduce categories from their description (objectives, requirements, technical considerations)
- Ask follow-up questions if needed - one question at a time, not a list
- Create file as
.knowledge-base/tasks/[task-id].md - Suggest relevant virtual experts to consult
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.
- 4d ago First seen · 65 lines · 0 tokens per session scan A 72732153383d
virtual-pm is a cursor rule published in the GitHub repository elmertoft/virtual-team-members (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 542 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 2026-08-31.
Other cursor rules, from other repositories
development-workflow
AAMAD modular development workflow for context-aware agent coordination.
feedback-enhanced
Enhanced feedback mechanism with 1-hour timeout - 增强反馈机制，1小时超时.
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
linear-in-review
After finishing a Linear issue, set its status to In Review (never Done).
sprint-planning
BMAD BMM Agent: sprint-planning.
generate-tasks
Understanding our task list for our project or how to make one from a PRD.