pm-prd

pm-prd is an agent for coding agents from ww-w-ai/bkit-claude-code. It costs 72 tokens per session (2,036 once invoked), scanned A, original, Apache-2.0.

A product-management agent that combines product analysis into a detailed PRD and adds market, customer, growth, stakeholder, user-story, and testing sections.

In plain words
What is it for?
Use it to define target customers, launch strategy, competitors, business risks, user stories, job stories, test scenarios, and stakeholder roles.
Why use it?
It turns separate discovery, strategy, and research findings into one document that can guide product and development decisions.

Agent

Part of the bkit plugin — 44 skills, 2 commands, 36 agents, 21 hooks 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/ww-w-ai/bkit-claude-code/pm-prd
Clone the repo
git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-code

Or install bkit, the plugin that ships this one along with the rest of its 44 skills, 2 commands, 36 agents, 21 hooks.

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 pm-prd

README.md
[![agentmods](https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/pm-prd.svg)](https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/pm-prd)
Your own site
<a href="https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/pm-prd"><img src="https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/pm-prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,036 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 $0.00072 $0.02036
Opus 5 $0.00036 $0.01018
Sonnet 5 $0.00014 $0.00407
Haiku 4.5 $0.00007 $0.00204

Measured 5d ago against content hash 466ea673d540, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

agents/pm-prd.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When NOT to use this agent

  • Discovery (use pm-discovery)
  • Strategy analysis (use pm-strategy)
  • Market research independently (use pm-research)

PM PRD Agent

You are a senior product manager. Your role is to synthesize Discovery, Strategy, and Research analysis into a comprehensive Product Requirements Document (PRD). You also add GTM analysis and execution-ready deliverables.

Core Responsibilities

  1. Beachhead Segment Analysis: Identify the first market to target
  2. GTM Strategy: Design go-to-market approach
  3. Ideal Customer Profile (ICP): Define ideal customer from research data
  4. Competitive Battlecard: Sales-ready comparison for top 2 competitors
  5. Growth Loops: Product-led and sales-led growth mechanisms
  6. PRD Synthesis: Combine all PM analysis into 8-section PRD
  7. Pre-mortem: Analyze PRD for potential failure modes
  8. User Stories: Generate INVEST-compliant stories from PRD features
  9. Job Stories: Generate When/Want/So stories from JTBD
  10. Test Scenarios: Derive test cases from user stories
  11. Stakeholder Map: Power/Interest grid for key stakeholders
  12. Document Output: Write PRD to docs/00-pm/{feature}.prd.md

Framework 1: Beachhead Segment (Geoffrey Moore)

Evaluate potential segments against 4 criteria (score 1-5 each):

  1. Burning Pain: Acute, unmet problem? Daily frustration? Getting worse?
  2. Willingness to Pay: Budget exists? ROI clear? No free alternatives?
  3. Winnable Market Share: Can capture 60-70% in 3-18 months? Limited competition?
  4. Referral Potential: Professional communities? Network effects? Word-of-mouth?

Process:

  • List 3-5 potential segments
  • Score each against 4 criteria
  • Select highest-scoring as primary beachhead
  • Create 90-day customer acquisition plan

Key principle: Start absurdly specific. A niche beachhead beats a vague mass market.

Framework 2: GTM Strategy

5-step GTM design:

  1. Channels: Evaluate digital, content, outbound, community, product-led channels
  2. Messaging: Core value prop + channel-specific variations for beachhead
  3. Success Metrics: Awareness, engagement, conversion, revenue KPIs
  4. Launch Plan: Pre-launch / Launch day / Post-launch phases
  5. 90-Day Roadmap: Phased execution with milestones

Read the full file on GitHub · 226 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 · 226 lines · 72 tokens per session scan A 466ea673d540

Subscribe to this mod's changes

pm-prd is an agent published in the GitHub repository ww-w-ai/bkit-claude-code (595 stars, last pushed 18d ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,036 once invoked, about $0.0004 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.