# product_manager

product_manager is a Claude Code subagent that turns a product question and available evidence into a clear decision. It helps compare options, set priorities, and define how to measure results.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 776 repo stars
- Author: AgenticOrgLab
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/AgenticOrgLab/ExecOrchestra/tree/HEAD/execorchestra/Pool/resources/agents/product_manager.md
- Updated: 2026-11-12
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/agenticorglab-product-manager

## What it does

The subagent writes a Markdown brief from a product question. It lays out the user problem, target segment, evidence, and assumptions, then compares options and recommends priorities, scope, and a roadmap.

The brief also covers success measures, guardrails, research gaps, validation experiments, dependencies, and release risks. The main input can include business context and constraints; research, metrics, and feedback are optional. It does not fabricate market facts, customer feedback, or delivery estimates.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/product_manager.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/product_manager.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/product_manager.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/AgenticOrgLab/ExecOrchestra/tree/HEAD/execorchestra/Pool/resources/agents/product_manager.md

## When to use it
- describe a user problem and its desired outcome
- compare product options and explain their priority
- choose success measures and validation experiments
- record dependencies and release risks

## Example prompts
- Draft a product brief for this issue and recommend what belongs in the next release.
- Compare ways to address this user problem and explain which option should come first.
- Turn these research notes and metrics into experiments for testing the product decision.

## Similar
- [product-strategist](https://affpapa.org/en/nevibecode/agents/product-strategist.md) — subagent · 3675 installs
- [product-marketing](https://affpapa.org/en/nevibecode/skills/product-marketing.md) — skill · 98400 installs
- [amazon-product-research](https://affpapa.org/en/nevibecode/skills/amazon-product-research.md) — skill · 78400 installs
- [product-photography](https://affpapa.org/en/nevibecode/skills/product-photography.md) — skill · 66100 installs
- [product-hunt-launch](https://affpapa.org/en/nevibecode/skills/product-hunt-launch.md) — skill · 65800 installs
- [product-manager](https://affpapa.org/en/nevibecode/agents/product-manager.md) — subagent · 1104 installs

From the same set: [agenticorglab/execorchestra](https://affpapa.org/en/nevibecode/by/agenticorglab/execorchestra.md) — 24 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
