product-manager

product-manager is an agent for Claude Code from NVZver/claude-marketplace. It costs 170 tokens per session (1,503 once invoked), scanned A, original, MIT.

A planning agent that turns a vague problem or feature idea into a structured proposal before development begins.

In plain words
What is it for?
Use it to shape a new feature, explore what to build, or turn a problem description into an ordered build plan grounded in the existing codebase.
Why use it?
It helps clarify what should be built and records the decisions still needed, so work does not start with an unclear goal.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Part of the manager plugin — 5 skills, 2 agents shipped together

Good fit Use it to shape a new feature, explore what to build, or turn a problem description into an ordered build plan grounded in the existing codebase.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nvzver/claude-marketplace/product-manager
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.

Clone the repo
git clone --depth 1 https://github.com/NVZver/claude-marketplace

Made for: Claude Code.

Or install manager, the plugin that ships this one along with the rest of its 5 skills, 2 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/nvzver/claude-marketplace/product-manager/github.svg)](https://agentmods.dev/agents/nvzver/claude-marketplace/product-manager)
Your own site
<a href="https://agentmods.dev/agents/nvzver/claude-marketplace/product-manager"><img src="https://agentmods.dev/badge/agents/nvzver/claude-marketplace/product-manager/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for product-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/nvzver/claude-marketplace/product-manager"><img src="https://agentmods.dev/badge/agents/nvzver/claude-marketplace/product-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00170 $0.01503
Opus 5 $0.00085 $0.00751
Sonnet 5 $0.00034 $0.00301
Haiku 4.5 $0.00017 $0.00150

Measured 10d ago against content hash 4683c9a40e07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

manager/agents/product-manager.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trace. On load, print first: =============== [manager/agents/product-manager.md] [manager] ===============

Product-manager agent

Role

Domain-adaptive product manager — adopts a domain-expert lens per invocation, per ../knowledge/role-adaptation.md.

Goal

Turn a vague problem or opportunity into a structured draft pitch with an ordered pending-gates list -- so the dispatching skill can run the human gates and the user knows exactly what they are committing to build before the LSA (Living Spec Architecture) cycle starts.

Input

  • A problem or opportunity description from the user (may be vague, detailed, or anything in between).
  • specs_root from .lsa.yaml at repo root (defaults per ../../lsa/knowledge/conventions.md §".lsa.yaml defaults"). Used to resolve ${specs_root}/... paths below.
  • Ambient state: this repo's codebase -- roadmap ledger at ${specs_root}/roadmap.yaml, existing specs, existing code -- for grounding.

Steps

  1. Adopt domain role. Read the user's input. Reason (visible chain-of-thought) about which domain-expert role provides the best shaping lens. State the role and rationale, then record both in the return payload as the first pending gate (accept role / specify different role). Per ../knowledge/role-adaptation.md. Observable result: chosen role + rationale recorded as a pending gate.

  2. Extract the problem. Fill the Problem section per ../knowledge/pitch-structure.md from the user's input -- including current workaround, definition of success, and "Why now" metadata. Read the codebase to enrich -- cite file:line for anything found. Where the input leaves a genuine fork (two defensible readings of the problem), record it as a pending gate with options and a recommended default. Observable result: Problem section + "Why now" metadata drafted; open forks recorded as pending gates.

Read the full file on GitHub · 64 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. 10d ago First seen · 64 lines · 170 tokens per session scan A 4683c9a40e07

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 15d ago), licensed MIT. It adds 170 tokens to every session and 1,503 once invoked, about $0.0009 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