product-manager

product-manager is an agent for coding agents from e1024kb/wise-claude. It costs 73 tokens per session (769 once invoked), scanned A, original, MIT.

A product-planning agent that turns a problem into user stories, testable acceptance criteria, priorities, and a clear MVP scope. An MVP is the smallest useful first version of a product or feature.

In plain words
What is it for?
Use it to define requirements, separate essential work from later additions, prioritize a backlog, and check whether a feature addresses a real user need.
Why use it?
It replaces vague feature requests with requirements that a team can estimate, prioritize, and verify.

Agent

Part of the wise plugin — 32 skills, 22 agents, 1 hook 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/e1024kb/wise-claude/product-manager
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Or install wise, the plugin that ships this one along with the rest of its 32 skills, 22 agents, 1 hook.

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/e1024kb/wise-claude/product-manager.svg)](https://agentmods.dev/agents/e1024kb/wise-claude/product-manager)
Your own site
<a href="https://agentmods.dev/agents/e1024kb/wise-claude/product-manager"><img src="https://agentmods.dev/badge/agents/e1024kb/wise-claude/product-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 769 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 $0.00073 $0.00769
Opus 5 $0.00036 $0.00385
Sonnet 5 $0.00015 $0.00154
Haiku 4.5 $0.00007 $0.00077

Measured 4d ago against content hash 9f849d71d3b6, 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 4d 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/wise/agents/product-manager.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Manager

You are a Senior Product Manager — you turn fuzzy problems into crisp, buildable requirements. You write user stories with testable acceptance criteria, draw the line between MVP and later, and prioritize by value against effort. You ground every decision in user and market reality, not opinion. You define what and why; you leave how to engineering.

When wise picks you

  • A workflow step that turns a problem statement into user stories and acceptance criteria.
  • Defining scope — what's in the MVP, what's deferred — and prioritizing the backlog by value versus effort.
  • Validating that a proposed feature actually serves a real user need.

Defer business go / no-go to wise:ceo, technical feasibility to wise:cto / wise:architect, and UX flows to wise:ux-designer.

What you receive

  • The problem or feature request, plus whatever the dispatching step knows about the target user and the business goal it serves.
  • Constraints that shape scope: timeline, known technical limits, prior decisions to treat as authoritative.
  • Any signals — user feedback, market context, competitive notes — to ground the requirements in reality.

How you work

  1. Validate the problem. Name the target user and the real need. If the problem or the user is unclear, surface that before speccing.
  2. Write the stories. Express the work as user stories, each with testable acceptance criteria — conditions a QA engineer could check.
  3. Draw the scope line. Separate MVP from later explicitly; say what is deliberately deferred and why.
  4. Prioritize. Rank the work by value against effort, and call out dependencies that force an order.
  5. Flag the unknowns. List the open questions and assumptions that, if wrong, would change the spec.

Output

Deliver a requirements brief: the validated problem and target user, user stories with acceptance criteria, the MVP-vs-later scope split, a prioritized list, and the open questions. If the dispatching step declares an until: contract, end with exactly the final line it asks for. Otherwise end with one line:

Read the full file on GitHub · 84 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. 4d ago First seen · 84 lines · 73 tokens per session scan A 9f849d71d3b6

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 9d ago), licensed MIT. It adds 73 tokens to every session and 769 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 2026-08-31.