A command that guides you through creating a Product Requirements Document, or PRD. A PRD is a written description of what a product feature should do and how it should be defined.

Brainstorming a feature, checking its name, creating a PRD file, checking for an existing PRD, and optionally creating project-tracking metadata.

It helps turn an early feature idea into a recorded, consistently named plan and can connect that plan to project tracking.

prd-new — Command for Claude Code by dtannen: A command that guides you through creating a Product…

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 commands/dtannen/pm/prd-new

Clone the repo

git clone --depth 1 https://github.com/dtannen/pm

Made for: Claude Code.

Or install pm, the plugin that ships this one along with the rest of its 4 skills, 13 commands, 5 agents, 3 hooks, 1 MCP server.

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/commands/dtannen/pm/prd-new.svg)](https://agentmods.dev/commands/dtannen/pm/prd-new)

Your own site

<a href="https://agentmods.dev/commands/dtannen/pm/prd-new"><img src="https://agentmods.dev/badge/commands/dtannen/pm/prd-new.svg" alt="Measured on agentmods" height="20"></a>

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,004 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.

Model	Per session	Once invoked
Fable 5	$0.00010	$0.01004
Opus 5	$0.00005	$0.00502
Sonnet 5	$0.00002	$0.00201
Haiku 4.5	$0.00001	$0.00100

Measured 4d ago against content hash be998d9f88ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-new 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 4d 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-plugin/commands/prd-new.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create New PRD

Launch guided brainstorming to create a comprehensive Product Requirements Document.

Usage

/pm:prd-new <feature-name>

Instructions

You are creating a PRD for: $ARGUMENTS

MCP Integration (optional)

Optionally seed an MCP epic/project mapping for this PRD to streamline later commands.

Full name: mcp__project-manager-mcp__create_task — Upserts project/epic via a seed task
Full name: mcp__project-manager-mcp__update_task — Attach PRD link/metadata to the seed

Suggested flow:

Create a seed tracking task: mcp__project-manager-mcp__create_task(name="PRD: $ARGUMENTS", project_name="{YourProject}", epic_name="$ARGUMENTS", ra_mode="standard", ra_score="4").
Update task with ra_metadata.prd_path = ".pm/prds/$ARGUMENTS.md" and a log_entry once the PRD is created.

1. Validate Feature Name

Must be kebab-case (lowercase letters, numbers, hyphens only)
Examples: user-authentication, payment-processing, notification-system
If invalid format, ask user to provide valid name

2. Check for Existing PRD

Check if .pm/prds/$ARGUMENTS.md already exists
If exists, ask: "PRD already exists. Overwrite? (yes/no)"
Only proceed with explicit 'yes'

3. Guided Discovery Process

Start with open-ended questions to understand the feature deeply:

Problem Discovery

"What specific problem does $ARGUMENTS solve?"
"Who experiences this problem and how often?"
"What happens if this problem isn't solved?"
"How are users currently working around this problem?"

User Journey Exploration

"Walk me through the ideal user experience for $ARGUMENTS"
"What would success look like from the user's perspective?"
"What are the key moments in this user journey?"
"Where might users get confused or frustrated?"

Technical Constraints

"Are there any technical limitations we need to consider?"
"What existing systems does this need to integrate with?"
"What performance requirements are critical?"
"Are there security or compliance considerations?"

Read the full file on GitHub · 119 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.

4d ago First seen · 119 lines · 10 tokens per session scan A be998d9f88ca

Subscribe to this mod's changes

prd-new is a command published in the GitHub repository dtannen/pm (0 stars, last pushed 10mo ago), licensed MIT. It adds 10 tokens to every session and 1,004 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 2026-08-31.

Planning Writing and docs

prd-new