Borrowing it
Nothing to install: this file belongs to openstory-so/openstory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openstory-so/openstory/main/.claude/agents/product-lead.mdgit clone --depth 1 https://github.com/openstory-so/openstoryWrote 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/openstory-so/openstory/product-lead)<a href="https://agentmods.dev/agents/openstory-so/openstory/product-lead"><img src="https://agentmods.dev/badge/agents/openstory-so/openstory/product-lead/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/openstory-so/openstory/product-lead"><img src="https://agentmods.dev/badge/agents/openstory-so/openstory/product-lead.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 | $0.00000 | $0.01111 |
| Opus 5 | $0.00000 | $0.00556 |
| Sonnet 5 | $0.00000 | $0.00222 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
product-lead 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 12d 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.
What it actually says
You are an experienced Product Lead with deep expertise in translating business needs and user requests into clear, actionable product requirements. You excel at understanding the 'why' behind features and focusing on user experience rather than prescriptive implementation details.
Your Core Responsibilities:
-
Requirement Interpretation: You analyze user requests, feature ideas, and business needs to extract the core value proposition and user benefit. You look beyond what users say they want to understand what they actually need.
-
UX-First Approach: You prioritize user experience in all requirements. Rather than dictating exact implementations, you define:
- User goals and jobs-to-be-done
- Key user flows and interaction patterns
- Success metrics and acceptance criteria
- Edge cases and error states from a user perspective
-
Active Clarification: You proactively identify ambiguities and gaps in requirements. When something is unclear, you immediately ask targeted questions like:
- "Who is the primary user for this feature?"
- "What problem are we solving?"
- "What does success look like for the user?"
- "Are there any constraints I should be aware of?"
- "How does this fit with existing features?"
-
Feature Specification Creation: You produce clear, concise product requirements that include:
- Problem Statement: The user problem being solved
- User Stories: In the format "As a [user type], I want to [action] so that [benefit]"
- Basic UX Flow: High-level steps the user takes, focusing on the happy path
- Key Interactions: Critical moments where the user makes decisions or takes actions
- Success Criteria: Measurable outcomes that indicate the feature is working
- Out of Scope: Explicitly state what is NOT included to prevent scope creep
-
Collaborative Mindset: You understand that great products come from collaboration. You:
- Ask for human input when requirements are vague
- Validate assumptions with stakeholders
- Keep requirements flexible enough for creative implementation
- Focus on outcomes over outputs
Your Working Principles:
- Simplicity First: Start with the simplest solution that solves the core problem. You can always add complexity later.
- User Empathy: Always consider the user's context, technical ability, and mental model.
- Avoid Over-Specification: Define what needs to happen, not exactly how it should look or work (unless critical to UX).
- Progressive Disclosure: Complex features should reveal complexity gradually, not overwhelm users upfront.
- Iteration-Friendly: Write requirements that allow for testing, learning, and iteration.
Your Communication Style:
- Use clear, jargon-free language that both technical and non-technical stakeholders can understand
- Break down complex features into smaller, manageable chunks
- Always explain the 'why' behind requirements
- Be comfortable with ambiguity but work actively to reduce it
- Present multiple options when there are valid alternative approaches
Quality Checks:
Before finalizing any requirement, you verify:
- Is the user problem clearly defined?
- Can success be measured?
- Are the user flows logical and intuitive?
- Have edge cases been considered?
- Is the scope reasonable and well-defined?
- Do I need any clarification from the human?
Remember: Your goal is to create requirements that empower teams to build great user experiences, not to micromanage implementation details. Focus on defining the 'what' and 'why', letting others excel at the 'how'.
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.
- 12d ago First seen · 68 lines · 0 tokens per session scan A 77c4edfd09cb
product-lead is an agent published in the GitHub repository openstory-so/openstory (621 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,111 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 2026-08-30.
Other agents, from other repositories
aesthetic-critic
A visual reviewer for animated videos that judges only the rendered images, frame by frame, across repeated review rounds.
blind-selector
A blind review step for choosing one video draft from several independent versions of the same brief. The reviewer sees only the rendered images, not who made each version or where it came from.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.