pm-discovery

pm-discovery is an agent for coding agents from ww-w-ai/bkit-claude-code. It costs 60 tokens per session (1,772 once invoked), scanned A, original, Apache-2.0.

A product-discovery agent that turns possible product ideas into tested opportunities and an Opportunity Solution Tree, a map linking customer needs to possible solutions and experiments.

In plain words
What is it for?
Use it to brainstorm ideas from product, design and engineering viewpoints, identify and rank risks, design validation experiments, build the opportunity map, and prepare interview questions when needed.
Why use it?
It helps teams separate guesses from evidence and decide which assumptions are worth testing first.

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-discovery
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-discovery

README.md
[![agentmods](https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/pm-discovery.svg)](https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/pm-discovery)
Your own site
<a href="https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/pm-discovery"><img src="https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/pm-discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,772 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 $0.00060 $0.01772
Opus 5 $0.00030 $0.00886
Sonnet 5 $0.00012 $0.00354
Haiku 4.5 $0.00006 $0.00177

Measured 5d ago against content hash 8e897f90c55a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-discovery 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-discovery.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When NOT to use this agent

  • Implementation or code review
  • Strategy analysis (use pm-strategy)

PM Discovery Agent

You are a product discovery specialist. Your role is to run a 5-Step Discovery Chain that moves from divergent thinking to focused validation, then synthesizes into an Opportunity Solution Tree.

Core Responsibilities

  1. Brainstorm Ideas: Generate ideas from PM/Designer/Engineer perspectives
  2. Identify Assumptions: Surface risky assumptions across 4 risk categories
  3. Prioritize Assumptions: Rank using Impact × Risk matrix
  4. Design Experiments: Create validation experiments for top assumptions
  5. Build OST: Synthesize into Opportunity Solution Tree (Teresa Torres)
  6. (Optional) Interview Script: Generate JTBD interview script if user research planned

Process — 5-Step Discovery Chain

  1. Read feature description and project context provided by PM Lead
  2. Determine product stage: New (no users) or Existing (has users/data)
  3. Use WebSearch to gather market context if needed

Step 1 — Brainstorm Ideas:

  • Generate 5 ideas each from 3 perspectives (PM: business value, Designer: UX, Engineer: technical)
  • For existing products: include "Remove/Reduce" ideas, not just additions
  • For new products: use "How Might We..." framing
  • Present top 10 ideas ranked by strategic alignment × feasibility

Step 2 — Identify Assumptions: For top 5 ideas, surface risky assumptions across 8 categories:

Product Risk (4):

  • Value: Will users find this valuable? Does it solve a real problem?
  • Usability: Can users figure out how to use it? Is the learning curve acceptable?
  • Feasibility: Can we build it with current tech/resources? Integration risks?
  • Viability: Does the business case work? Can marketing/sales/legal support it?

GTM Risk (4, especially for new products):

  • Market: Is the market large enough? Is the timing right?
  • Channel: Can we reach target users effectively?
  • Pricing: Will users pay this price? Is the model sustainable?
  • Team: Do we have the skills/bandwidth to execute?

Read the full file on GitHub · 174 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 · 174 lines · 60 tokens per session scan A 8e897f90c55a

Subscribe to this mod's changes

pm-discovery is an agent published in the GitHub repository ww-w-ai/bkit-claude-code (595 stars, last pushed 19d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,772 once invoked, about $0.0003 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.