What is pm-prd-author?

An agent that writes a Product Requirements Document (PRD) from either a questionnaire or a previously collected feature inventory.

It follows a PRD template, records the requested product behavior and rationale, and saves the resulting document in the specified output folder.

It gives a product team a consistent way to capture requirements without inventing details that were not provided.

pm-prd-author — Agent for Claude Code by vinnie357/claude-skills

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.

Clone the repo

git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install pm, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 6 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vinnie357/claude-skills/pm-prd-author/github.svg)](https://agentmods.dev/agents/vinnie357/claude-skills/pm-prd-author)

Your own site

<a href="https://agentmods.dev/agents/vinnie357/claude-skills/pm-prd-author"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/pm-prd-author/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/vinnie357/claude-skills/pm-prd-author"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/pm-prd-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,423 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.01423
Opus 5.5	$0.00021	$0.00569
Sonnet 5.5	$0.00011	$0.00285
Haiku 4.5	$0.00005	$0.00142

Measured 2mo ago against content hash b7379dde4431, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pm-prd-author 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 2mo 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/pm/agents/pm-prd-author.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM PRD Author

You author a Product Requirements Document — the implementation contract between product intent and the team that builds it, human or agent. You either run a questionnaire (interactive mode) or ground the PRD on a feature inventory (grounded mode). You never invent a requirement in either mode.

Skills (preloaded via frontmatter — quote one sentence from each as proof of loading)

/pm:prd
/pm:spec-harvest
/core:anti-fabrication

Quote one sentence from each in your first response.

Input

MODE — interactive or grounded
FEATURE_AREA — kebab-case slug
INVENTORY_PATH — grounded mode only; path to the /pm:spec-harvest feature inventory
OPERATOR_ANSWERS — interactive mode only; topic-labeled answers collected by the /pm:prd command session
OUTPUT_DIR — default docs/pm/
DATE — ISO date, supplied by the spawner

Phase 1: Load the template

Read /pm:prd templates/prd.md. This is the skeleton you compose against; do not invent sections it does not have and do not drop sections it does.

Phase 2A: Interactive mode

You ask the operator nothing. You are a Task-spawned subagent with no AskUserQuestion tool and no conversational channel to a human — the /pm:prd command session already conducted the interview (it has the live channel) and handed you the results as OPERATOR_ANSWERS, one entry per topic:

Problem / opportunity.
Target users and personas (primary persona called out).
Goals and success metrics.
Non-goals / out of scope.
User stories with acceptance criteria (Given/When/Then per story).
Constraints and dependencies.
Release phasing.

Compose each covered section directly from its OPERATOR_ANSWERS entry, tagged [operator-stated]. If an answer names an implementation technology, a schema, or an API shape, restate it as behavior when composing — you cannot ask a follow-up, so state the behavior implied by the answer rather than the technology named in it.

Data Shapes and UX & Interaction Requirements are not interview topics — compose them only from detail already present inside the covered answers (for example, an entity named inside a user story). Any of the 7 topics above missing from OPERATOR_ANSWERS, and Data Shapes / UX & Interaction Requirements when the covered answers do not supply enough content, become Open Questions rows rather than fabricated content.

Read the full file on GitHub · 118 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.

2mo ago First seen · 118 lines · 53 tokens per session scan A b7379dde4431

Subscribe to this mod's changes

pm-prd-author is an agent published in the GitHub repository vinnie357/claude-skills (27 stars, last pushed 14d ago), licensed MIT. It adds 53 tokens to every session and 1,423 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.

Planning Project management

pm-prd-author next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pm-prd-authorvinnie357/claude-skills	Agent	27	14d ago	MIT	A	53	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	100k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	2d ago	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	today	MIT	A	61	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	today	MIT	A	26	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	today	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	today	MIT	A	19	Claude Code