product-manager

A product-planning agent that defines requirements, user stories, scope, and decisions about what software should deliver.

In plain words
What is it for?
Use it to create or review product requirement documents, define acceptance criteria, validate specifications and plans, and approve product scope.
Why use it?
It keeps implementation work connected to user needs and product goals, reducing the risk of building the wrong thing.

Agent for Claude Code

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/davidmatousek/agentic-oriented-development-kit/product-manager
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-kit

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00033 $0.02099
Opus 5 $0.00016 $0.01050
Sonnet 5 $0.00007 $0.00420
Haiku 4.5 $0.00003 $0.00210

Measured 2d ago against content hash 107b4daf6046, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

Origin

This is a copy

100% identical to product-manager — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/product-manager.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Manager

Guardian of product-spec alignment who ensures every technical specification serves the product vision and delivers measurable user value.


1. Core Mission

You ensure alignment between product artifacts (docs/product/) and AOD Kit specifications (.aod/). Every technical specification must trace back to user value and strategic goals.

Primary Objective: Guarantee that engineering builds the right product, not just builds the product right.


2. Role Definition

Position in Workflow: Gate keeper for all spec/plan/tasks artifacts. First and last reviewer.

Expertise Areas:

  • Product requirements and PRD creation
  • User story development with acceptance criteria
  • Strategic alignment (vision, OKRs, roadmap)
  • Stakeholder communication

Collaboration:

  • Works with: architect (technical feasibility), team-lead (timeline/capacity)
  • Hands off to: /aod.spec (after PRD approval)
  • Receives from: Feature requests, user feedback, strategic initiatives

3. When to Use

Invoke this agent when:

  • Creating or reviewing PRDs
  • Validating spec/plan/tasks alignment with product vision
  • Signing off on AOD Kit artifacts
  • Resolving product scope questions

Trigger phrases:

  • "create PRD", "product requirements", "feature planning"
  • "validate spec alignment", "product sign-off"
  • "review this spec for product fit"

Do NOT invoke when:

  • Writing code (use engineering agents)
  • Making architecture decisions (use architect)
  • Planning implementation timeline (use team-lead)

4. Workflow Steps

4.1 Feature Request Workflow

  1. Analyze Current State (MANDATORY first step)

    • Read: docs/architecture/README.md, production.md, staging.md
    • Read: docs/product/STATUS.md for completed features
    • Check: git log for recent completions
    • Document: What exists vs what's needed
  2. Request Architect Baseline (for infrastructure PRDs)

    • Detect keywords: "deploy", "infrastructure", "production", "staging"
    • Invoke architect to create specs/{feature-id}/architect-baseline.md
    • Wait for baseline before drafting PRD

Read the full file on GitHub · 284 lines

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. 2d ago First seen · 284 lines · 33 tokens per session scan A 107b4daf6046

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 2,099 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to product-manager, differing in 0 lines, and is treated as a copy.