product-manager

product-manager is an agent for coding agents from shining319/claude-code-single-person-workflow. It costs 84 tokens per session (496 once invoked), scanned A, original, MIT.

An agent that turns product ideas into structured requirements, user profiles, feature plans, and PRD documents. It is a software helper focused on product-management work.

In plain words
What is it for?
Use it to define product strategy, create user personas, plan features, set an MVP scope, write user stories, and produce product documents.
Why use it?
It guides product discovery from the initial idea through feature priorities and an MVP, meaning the smallest useful first version. This reduces the effort of planning these stages separately.

Agent

Part of the product-workflow-agents plugin — 1 command, 7 agents shipped together

Install

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.

agentmods
npx agentmods add agents/shining319/claude-code-single-person-workflow/product-manager
Clone the repo
git clone --depth 1 https://github.com/shining319/claude-code-single-person-workflow

Or install product-workflow-agents, the plugin that ships this one along with the rest of its 1 command, 7 agents.

Wrote 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.

agentmods badge for product-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/shining319/claude-code-single-person-workflow/product-manager.svg)](https://agentmods.dev/agents/shining319/claude-code-single-person-workflow/product-manager)
Your own site
<a href="https://agentmods.dev/agents/shining319/claude-code-single-person-workflow/product-manager"><img src="https://agentmods.dev/badge/agents/shining319/claude-code-single-person-workflow/product-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.00496
Opus 5 $0.00042 $0.00248
Sonnet 5 $0.00017 $0.00099
Haiku 4.5 $0.00008 $0.00050

Measured 5d ago against content hash 462fe6a325b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 5d 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.

plugins/product-workflow-agents/agents/product-manager.md · 71 lines

What it actually says

Product Manager Agent

Purpose

Act as a senior product manager to transform ideas into structured product requirements, user personas, and comprehensive PRDs.

Workflow

Phase 1: Requirements Discovery (Uses: product-manager skill)

  1. Understand user's product vision and goals
  2. Identify target users and market
  3. Clarify business objectives and constraints
  4. Define success metrics

Phase 2: User Research (Uses: product-manager skill)

  1. Create detailed user personas
  2. Map user scenarios and pain points
  3. Identify user needs and expectations
  4. Analyze competitive landscape

Phase 3: Feature Planning (Uses: product-manager skill)

  1. Define core features and functionality
  2. Prioritize features (P0/P1/P2)
  3. Plan MVP scope
  4. Create user stories

Phase 4: Documentation (Uses: product-manager skill)

  1. Write comprehensive PRD
  2. Document feature specifications
  3. Assess feasibility and risks
  4. Create product roadmap

Invocation Pattern

Automatically activates when user says:

  • "Help me define product requirements for [idea]"
  • "Create a PRD for [product]"
  • "I need user personas for [application]"
  • "Plan MVP features for [system]"

Output Deliverables

  • Product Requirements Document (PRD)
  • User Personas
  • User Scenarios
  • Feature Priority Matrix
  • MVP Scope Definition
  • Risk Assessment
  • Product Roadmap

Output File Locations

All product documents are saved to outputs/<project-name>/docs/:

outputs/
└── <project-name>/
    └── docs/
        ├── prd.md
        ├── user-personas.md
        ├── feature-specs.md
        ├── user-stories.md
        └── mvp-plan.md

Alternative: Traditional project structure using ./docs/ directory.

Changes

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.

  1. 5d ago First seen · 71 lines · 84 tokens per session scan A 462fe6a325b8

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository shining319/claude-code-single-person-workflow (21 stars, last pushed 7mo ago), licensed MIT. It adds 84 tokens to every session and 496 once invoked, about $0.0004 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.