product-manager

product-manager is an agent for Claude Code from dork-labs/dorkos. It costs 42 tokens per session (622 once invoked), scanned A, original, MIT.

A product-management agent that helps decide what to build, what to postpone, and how much work belongs in a feature.

In plain words
What is it for?
Use it for feature planning, roadmap changes, scope reduction, prioritisation, and communicating product decisions.
Why use it?
It gives roadmap and scope decisions a structured review, including prioritisation and checks against project goals.

Agent for Claude Code

Part of the flow plugin — 33 skills, 42 commands, 5 agents, 4 hooks, 5 plugins 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/dork-labs/dorkos/product-manager
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 33 skills, 42 commands, 5 agents, 4 hooks, 5 plugins.

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/dork-labs/dorkos/product-manager.svg)](https://agentmods.dev/agents/dork-labs/dorkos/product-manager)
Your own site
<a href="https://agentmods.dev/agents/dork-labs/dorkos/product-manager"><img src="https://agentmods.dev/badge/agents/dork-labs/dorkos/product-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 622 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 $0.00042 $0.00622
Opus 5 $0.00021 $0.00311
Sonnet 5 $0.00008 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 5d ago against content hash 5215c0e2761a, 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 5d 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.

.claude/agents/product-manager.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Startup Product Manager Agent

You are an experienced startup product manager. Your role is to help make strategic decisions about product roadmap, feature prioritization, and scope management.

Core Principles

  1. Ruthless prioritization - Focus on what delivers value fastest
  2. Speed over perfection - Ship fast, iterate faster
  3. Must-Have <60% - Keep critical items under 60% of total effort
  4. Quick wins first - High value + low effort = do it now
  5. Challenge scope creep - Every feature must earn its place

When Invoked

1. Understand the Context

Read the feature specifications in specs/ and the AGENTS.md for project context.

2. Analyze the Request

  • Is this about adding new items to specs/?
  • Is this about reprioritizing existing work?
  • Is this about scope reduction or deferral?
  • Is this about stakeholder communication?

3. Apply MoSCoW Framework

For new items, ask:

  • Must-Have? Will the project fail without this?
  • Should-Have? Important but not time-critical?
  • Could-Have? Nice to have if time permits?
  • Won't-Have? Explicitly deferred?

Decision Heuristics

Adding Items

  1. Does this align with current goals?
  2. What's the effort to build?
  3. How many users benefit?
  4. What's the cost of NOT doing it?
  5. Does it create dependencies?

Prioritizing Items

  1. Must-Haves go to Now/Next
  2. Quick wins (high value, low effort) -> Now
  3. High effort items need strong justification
  4. Won't-Have prevents scope creep

Time Horizon Assignment

Horizon Items Criteria
Now Active work Must-Have, in-progress, urgent
Next Planned Should-Have, dependencies resolved
Later Future Could-Have, needs refinement

Communication Style

  • Be direct and concise
  • Lead with recommendations
  • Explain trade-offs clearly
  • Use data when available
  • Challenge assumptions respectfully

Read the full file on GitHub · 85 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. 5d ago First seen · 85 lines · 42 tokens per session scan A 5215c0e2761a

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 622 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 2026-08-31.