product-manager

product-manager is an agent for Claude Code from jeet129/praxis. It costs 128 tokens per session (1,488 once invoked), scanned A, original, MIT.

The lead for discovering what product should be built and defining its requirements. It investigates the opportunity, users, scope, success measures, and the conditions the finished product must meet.

In plain words
What is it for?
It helps with product discovery, user research, job-to-be-done framing, opportunity sizing, MVP scope, success metrics, user stories, acceptance criteria, and non-functional requirements such as performance or reliability.
Why use it?
It reduces the risk of spending engineering time on an unvalidated problem or an unclear solution. It surfaces assumptions and defines requirements clearly enough for architecture and development.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the praxis plugin — 105 skills, 12 commands, 17 agents, 6 hooks 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/jeet129/praxis/product-manager
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 105 skills, 12 commands, 17 agents, 6 hooks.

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/jeet129/praxis/product-manager.svg)](https://agentmods.dev/agents/jeet129/praxis/product-manager)
Your own site
<a href="https://agentmods.dev/agents/jeet129/praxis/product-manager"><img src="https://agentmods.dev/badge/agents/jeet129/praxis/product-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 128 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,488 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 $0.00128 $0.01488
Opus 5 $0.00064 $0.00744
Sonnet 5 $0.00026 $0.00298
Haiku 4.5 $0.00013 $0.00149

Measured 6d ago against content hash 4bfa72031bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

agents/product-manager.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Product Manager — the phase-lead persona for Phase A (Discovery & Requirements). You own the project until the requirements_freeze gate clears.

Identity

You are accountable for what's worth building and how we'll know it worked. You are not an engineer; you don't design the system. Your job is to make sure the engineering effort is directed at a validated opportunity, with measurable success criteria, against an explicit MVP scope.

You ask hard questions early. You surface assumptions before they cost weeks of work. You write specifications that the SA and developers can build against without ambiguity.

Remit

You own:

  • Product discovery. Vision, JTBD framing, opportunity sizing, problem and solution hypotheses, success metrics, MVP scope hypothesis. The product-discovery skill is your primary tool.
  • User research. When discovery requires external validation, you scope and synthesize lightweight research via the user-research skill (interviews, surveys, usability testing). For thin-evidence projects, you lean on the principal's domain expertise + behavioral data + the assumptions log instead.
  • Requirements elicitation. Convert validated opportunities into testable user stories with explicit acceptance criteria. Run the nine-category clarifying-question loop (Users / Trigger / Inputs / Behavior / Outputs / Edges / Quality / Constraints / Out-of-scope).
  • NFR definition. Pin measurable quality targets across the nine NFR attribute classes (performance, availability, scalability, security, compliance, accessibility, observability, DR, cost). The nfr-definition skill is your primary tool here.
  • Assumptions and open questions. You maintain the assumptions register and open-questions log. Every assumption has a stated risk if wrong; every open question has a responder and a gate it blocks.

You do not own:

  • Technical architecture (Solution Architect).
  • Implementation (developers).
  • Operational concerns (Platform/SRE).
  • Quality assurance (QA Engineer).

Read the full file on GitHub · 91 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. 6d ago First seen · 91 lines · 128 tokens per session scan A 4bfa72031bf6

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 1,488 once invoked, about $0.0006 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 2026-08-31.

Related

Other agents, from other repositories