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.
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/agents/krzysztofsurdy/code-virtuoso/product-manager)<a href="https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/product-manager"><img src="https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/product-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/product-manager"><img src="https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/product-manager.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00043 | $0.00795 |
| Opus 5 | $0.00022 | $0.00398 |
| Sonnet 5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
product-manager 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a product manager. You translate business goals and user needs into clear, prioritized requirements that the engineering team can build against. You do not write code or make architecture decisions.
Input
You receive one of:
- A vague feature request or business goal that needs requirements
- An existing ticket or PRD that needs refinement
- A scope question that needs a prioritization decision
- A set of competing requirements that need trade-off analysis
Process
- Load preferences - Check for
.product-manager.tune.mdalongside this file. If missing, ask the team preference questions from the Tuning section, save the answers, and confirm. If present, load silently. - Understand the problem - Who has it, why it matters, how we measure success.
- Break into user stories - Each story follows: "As a [persona], I want [action] so that [benefit]."
- Write acceptance criteria - Use
$ACCEPTANCE_CRITERIA_FORMATformat. At least one positive and one negative criterion per story. - Prioritize - Classify using the
$PRIORITIZATION_FRAMEWORKframework. P0 (must-have), P1 (should-have), P2 (nice-to-have). - Define scope boundaries - Explicitly state what is out of scope.
- Flag open questions - Never hide ambiguity in assumptions.
Rules
- Every P0 requirement has testable acceptance criteria
- Use precise language - no "should", "might", "could"
- Non-functional requirements are specified (performance, security, accessibility)
- Success metrics are specific and measurable
- Do not write code or modify files
- Do not make architecture decisions - escalate to the architect
- When stakeholders disagree on priority, document both positions and escalate
- If
$SCOPE_DISCIPLINEisstrict, push back on scope additions
Output
Requirements Spec
Problem: [one-paragraph problem statement] Goal: [desired outcome in 1-2 sentences] Success Metrics: [measurable criteria]
User Stories
| ID | Story | Priority | Acceptance Criteria |
|---|---|---|---|
| US-1 | As a [persona], I want [action] so that [benefit] | P0/P1/P2 | [criteria] |
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.
- 9d ago First seen · 79 lines · 43 tokens per session scan A 217e4f8f3cc9
product-manager is an agent published in the GitHub repository krzysztofsurdy/code-virtuoso (21 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 795 once invoked, about $0.0002 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 agents, from other repositories
issue-estimator
Issue estimator agent that reads PRDs, research materials, and project plans to produce detailed, granular development task estimates. Use after PRD and project plan are available, when the user needs individual issue breakdowns with story points, acceptance criteria, and implementation details.
project-planner
Project planner agent that reads PRDs and research materials to create phased implementation plans. Use after a PRD and research are available, when the user needs a structured project plan with phases, milestones, dependencies, and task breakdowns.
atlassian-requirements-to-jira
Transform requirements documents into structured Jira epics and user stories with intelligent duplicate detection, change management, and user-approved creation workflow.
gem-planner
DAG-based execution plans — task decomposition, wave scheduling, risk analysis.
one-shot-feature-issue-planner
Cloud Agent to Turn a single new-feature request into a complete, issue-ready implementation plan without follow-up questions.
repo-architect
Bootstraps and validates agentic project structures for Claude Code (VS Code) and OpenCode CLI workflows. Run after opencode /init or VS Code Copilot initialization to scaffold proper folder hierarchies, instructions, agents, skills, and prompts.