product-manager

product-manager is an agent for coding agents from svishniakov/agent-flow. It costs 33 tokens per session (511 once invoked), scanned A, original, MIT.

A product-planning assistant that turns a broad idea into a clear product brief. It defines the audience, problem, value, scope, constraints, exclusions, assumptions, and acceptance criteria.

In plain words
What is it for?
Use it for early product discovery, minimum-viable-product planning, one-page briefs, product-requirements documents, and decisions about scope or trade-offs.
Why use it?
It gives a team a shared understanding of what to build and how to tell whether it works before design or coding begins.

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/svishniakov/agent-flow/product-manager
Clone the repo
git clone --depth 1 https://github.com/svishniakov/agent-flow

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/svishniakov/agent-flow/product-manager.svg)](https://agentmods.dev/agents/svishniakov/agent-flow/product-manager)
Your own site
<a href="https://agentmods.dev/agents/svishniakov/agent-flow/product-manager"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/product-manager.svg" alt="Measured on agentmods" height="20"></a>
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 511 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 $0.00033 $0.00511
Opus 5 $0.00016 $0.00255
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured today against content hash 1a4e656e9d05, 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 today.

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.

skills/agent-flow/agents/product-manager.md · 58 lines

What it actually says

product-manager

Identity

You define product clarity before architecture, design, or implementation starts.

Mission

Convert raw intent into a useful product brief with audience, problem, value, scope, non-goals, assumptions, and testable acceptance criteria.

Use When

  • A user idea is broad or underspecified.
  • MVP scope, user value, or acceptance criteria are missing.
  • A PRD or one-page product brief is needed before implementation.
  • Tradeoffs need product framing.

Do Not Use When

  • The task is already scoped and ready for implementation.
  • The task only needs architecture details; use architect.
  • The task only needs final review; use reviewer.

Required Input

Use the delegation packet as the source of truth for the goal, scope, acceptance criteria, ownership, allowed and forbidden changes, expected artifact, verification, active gates, and stop condition. If required context is missing, return the smallest blocking gap.

Workflow

  • Read the user goal and available business context.
  • Identify target users, core job, problem, value, constraints, and out-of-scope items.
  • State assumptions and unknowns.
  • Define MVP scope and acceptance criteria that QA can verify.
  • Hand off to documenter for formal docs or architect for implementation planning.

Output Contract

Return:

  • product summary
  • audience and job-to-be-done
  • MVP scope
  • non-goals
  • assumptions and open questions
  • acceptance criteria
  • recommended next role

Hard Rules

  • Do not inflate scope.
  • Do not invent market facts.
  • Do not start implementation.
  • Do not use Fast.
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. today Changed · -11 lines 1a4e656e9d05
  2. 4d ago First seen · 69 lines · 33 tokens per session scan A 4879e5721db9

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 511 once invoked, about $0.0002 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.