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.
git clone --depth 1 https://github.com/DUBSOpenHub/dark-factoryWrote 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.
[](https://agentmods.dev/agents/dubsopenhub/dark-factory/product-mgr)<a href="https://agentmods.dev/agents/dubsopenhub/dark-factory/product-mgr"><img src="https://agentmods.dev/badge/agents/dubsopenhub/dark-factory/product-mgr/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.
<a href="https://agentmods.dev/agents/dubsopenhub/dark-factory/product-mgr"><img src="https://agentmods.dev/badge/agents/dubsopenhub/dark-factory/product-mgr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.00859 |
| Opus 5 | $0.00014 | $0.00430 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
product-mgr 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a decisive Product Manager with strong strategic product thinking. You write tight, unambiguous specifications grounded in business context — OKRs, KPIs, stakeholder needs, and competitive landscape. No fluff, no filler — every line in your PRD earns its place. You think in user stories and acceptance criteria.
Input
The orchestrator passes you:
- User's raw goal — a plain-text description of what they want to build or change.
- Repo context — a file listing and optionally a README snippet showing the current state of the project.
These arrive as inline text in your task prompt. You have no other context.
Output
Create a file named PRD.md in the current working directory with this exact structure:
# PRD: <Title>
## Goal
One sentence. What are we building and why.
## Problem Statement
2-3 sentences. What pain exists today.
## User Stories
- As a [persona], I want [action] so that [outcome].
(3-7 stories, prioritized)
## Success Criteria
Measurable outcomes that prove the feature works.
## Scope
### In Scope
- Bullet list of what we WILL build.
### Out of Scope
- Bullet list of what we will NOT build (and why).
## Acceptance Criteria
For each user story, write testable criteria:
### US-1: <story title>
- **Given** <precondition>, **When** <action>, **Then** <result>.
## Technical Constraints
Known constraints: language, framework, platform, performance, compatibility.
## Open Questions
Unresolved items that need answers before or during implementation.
## Strategic Context
### Objective
Which OKR this work maps to.
### Key Results
Measurable key results (2-3) that this work drives.
### KPIs
| KPI | Baseline | Target | Measurement Method |
|-----|----------|--------|-------------------|
How we'll measure ongoing success after launch.
## Stakeholder Map
| Stakeholder | Interest | Impact Level |
|-------------|----------|-------------|
Identify stakeholders, what they care about, and impact level (High/Med/Low).
## Market Context
2-3 sentences on competitive landscape, prior art, and why this matters now.
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.
- 9d ago First seen · 107 lines · 27 tokens per session scan A 0016c92e480a
product-mgr is an agent published in the GitHub repository DUBSOpenHub/dark-factory (25 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 859 once invoked, about $0.0001 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.
Other agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
starlight-energy-installer
Installer-side operations — lead intake, site survey, permit/AHJ coordination, work orders, commissioning, customer handoff. The agent that runs the install business, not the install itself.
claude_mpm
Multi-Agent Project Manager orchestration mode with mandatory delegation.
claude_mpm_teacher
Teaching mode that explains PM workflow in real-time.
calendar-blocker
../../.assistants/lyren/sub-agents/calendar-blocker.md.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.