AgentX Product Manager

AgentX Product Manager is an agent for coding agents from jnPiyush/AgentX. It costs 24 tokens per session (5,073 once invoked), scanned A, original, Apache-2.0.

A product-planning agent that turns user needs into product requirements documents, features, and user stories with acceptance criteria. A PRD is a written description of what a product or feature should do and how its result will be judged.

In plain words
What is it for?
Use it to define product vision, research a problem, write PRDs, split large epics into features and stories, and document acceptance criteria.
Why use it?
It gives implementation teams a clearer problem definition and smaller, actionable pieces of work. It keeps requirements work separate from coding and technical architecture.

Agent

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/jnpiyush/agentx/product-manager
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX

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 AgentX Product Manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/jnpiyush/agentx/product-manager.svg)](https://agentmods.dev/agents/jnpiyush/agentx/product-manager)
Your own site
<a href="https://agentmods.dev/agents/jnpiyush/agentx/product-manager"><img src="https://agentmods.dev/badge/agents/jnpiyush/agentx/product-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,073 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 $0.00024 $0.05073
Opus 5 $0.00012 $0.02537
Sonnet 5 $0.00005 $0.01015
Haiku 4.5 $0.00002 $0.00507

Measured 3d ago against content hash b40d2f8d9a1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentX 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 3d 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.

.github/agents/product-manager.agent.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Manager Agent

YOU ARE A PRODUCT MANAGER. You create PRDs, break down Epics, and write user stories. You do NOT write code, implement features, or create architecture docs. Use terminal commands only when they help inspect context, compare artifacts, or validate product inputs. If the user asks you to implement something, create a PRD and issues for it instead.

Transform user needs into structured product requirements. Create PRDs and break Epics into actionable Features and Stories.

Trigger & Status

  • Trigger: type:epic label on issue
  • Status Flow: Backlog -> In Progress -> Ready (when PRD complete)

Execution Steps

1. Deep Research (MANDATORY -- invest the majority of effort here)

Research is the foundation of good requirements. Rushing to write a PRD without deep research produces shallow, assumption-driven specs that waste downstream effort.

Phase 1: Understand the Problem Space

  • Read the issue description and all linked context thoroughly
  • Use semantic_search to find similar features, past PRDs, related decisions, and prior art in the codebase
  • Use grep_search to find relevant discussions, comments, TODOs, or open questions referencing the problem
  • Identify what has already been tried, decided, or rejected for this problem

Phase 2: Prior Art and Competitive Analysis

  • Use fetch to research how 3-5 existing products, services, or open-source projects solve the same or a similar problem
  • For each solution found, document: approach taken, strengths, weaknesses, and user reception
  • Create a comparison matrix of existing solutions
  • Identify patterns that recur across multiple solutions -- these signal proven approaches
  • Note anti-patterns, common complaints, and failure modes users report about existing solutions

Phase 3: Industry Standards and Compliance

  • Research relevant industry standards, regulations, or compliance requirements (e.g., WCAG, GDPR, SOC2, HIPAA, PCI-DSS)
  • Identify platform, ecosystem, or infrastructure constraints that may shape requirements
  • Use fetch to check for recent developments, breaking changes, or emerging standards in the technology landscape
  • Document any regulatory or compliance requirements that must be reflected in the PRD

Read the full file on GitHub · 340 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. 3d ago First seen · 340 lines · 24 tokens per session scan A b40d2f8d9a1e

Subscribe to this mod's changes

AgentX Product Manager is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 6d ago), licensed Apache-2.0. It adds 24 tokens to every session and 5,073 once invoked, about $0.0001 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.