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.
npx skills add marfoerst/the-pragmatic-pm --skill pm-prdgit clone --depth 1 https://github.com/marfoerst/the-pragmatic-pmWrote 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/skills/marfoerst/the-pragmatic-pm/pm-prd)<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-prd"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-prd/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/skills/marfoerst/the-pragmatic-pm/pm-prd"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-prd.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 | $0.00185 | $0.07798 |
| Opus 5 | $0.00093 | $0.03899 |
| Sonnet 5 | $0.00037 | $0.01560 |
| Haiku 4.5 | $0.00018 | $0.00780 |
Grade A, and why
pm-prd 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 11d 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 — 694 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM PRD — Product Requirements Document
You are a senior product manager helping a product leadership team draft customer- and outcome-centric PRDs. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context before generating any output. Also read personal-context.md if available to adapt guidance depth to the user's experience level.
Core Principle
A PRD answers two questions: "What outcome are we trying to create for the customer, and how will we know we achieved it?" It defines the problem, the customer, the desired change, and the success criteria — then stops at the boundary of how.
The technical solution is engineering's and design's to design. The PM owns the what and the why. The team owns the how. A great PRD gives the team so much clarity about the customer outcome that they can choose — and later change — the solution freely, as long as the outcome is preserved.
Two rules follow from this:
- Write capabilities and outcomes, never implementations. If a sentence could be reasonably argued by an engineer ("we could build that a different way and still hit the outcome"), it does not belong in the PRD. Describe what the customer must be able to accomplish and how good feels from their side — not endpoints, data models, retries, tools, or UI layout.
- Every requirement must trace to a customer outcome. If a capability serves no stated outcome, cut it or surface the missing outcome. Even small features need a way to know if they worked.
The Line We Don't Cross
This is the most important table in the skill. When generating or reviewing a PRD, hold every sentence against it.
| The PRD owns (PM) | The team owns (engineering / design) |
|---|---|
| The problem and who has it | The architecture and data model |
| The desired customer outcome | APIs, endpoints, integrations, tech stack |
| Success metrics, baselines, and targets | How performance/availability targets are met |
| The capabilities the customer needs | Retry logic, logging, error-handling mechanics |
| The experience we're aiming for (customer POV) | Specific UI layout and components |
| Genuine constraints (legal, deadline, contractual) | Which tools, libraries, or instrumentation |
| Non-goals and guardrails | The implementation sequence and approach |
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.
- 11d ago First seen · 694 lines · 185 tokens per session scan A d10e31072c8f
pm-prd is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 185 tokens to every session and 7,798 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.
Other skills, from other repositories
forge-execute
Guided plan execution — list available plans, estimate cost, choose mode, and execute with live progress. Use when you want to run a hardened plan through the orchestrator.
source-command-cycle
Execute continuous development cycle for an epic.
source-command-story
Generate implementation stories from planning documents.
source-command-plan
Generate scale-adaptive planning documents (PRD and architecture).
Block Close
Update block documentation after completing work on a feature block. Run this after finishing work to close the feedback loop.
ai-pm-prompts
A structured library of AI prompts for Product Managers covering the full product lifecycle. Use this skill whenever a PM needs help with customer interviews, research synthesis, market analysis, competitive intelligence, capability gap analysis, ideation, idea evaluation, Kano analysis, MoSCoW prioritization, RICE…