product-decision

product-decision is a command for Claude Code from heznpc/PLOIDY. It costs 46 tokens per session (892 once invoked), scanned A, original, MIT.

A review command for deciding whether a product or feature should be built, using both existing product context and a fresh reader's view.

In plain words
What is it for?
Use it to examine a product or feature proposal, compare its mechanism with alternatives, label sunk-cost reuse, and assess risks from multiple viewpoints.
Why use it?
It helps expose decisions driven by past investment or habit rather than current user needs. It also identifies who benefits, who may be harmed, and whether reuse is genuinely necessary.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

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/heznpc/ploidy/product-decision
Clone the repo
git clone --depth 1 https://github.com/heznpc/PLOIDY

Made for: Claude Code.

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 product-decision

README.md
[![agentmods](https://agentmods.dev/badge/commands/heznpc/ploidy/product-decision.svg)](https://agentmods.dev/commands/heznpc/ploidy/product-decision)
Your own site
<a href="https://agentmods.dev/commands/heznpc/ploidy/product-decision"><img src="https://agentmods.dev/badge/commands/heznpc/ploidy/product-decision.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 892 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 5.1 $0.00046 $0.00892
Opus 5 $0.00023 $0.00446
Sonnet 5 $0.00009 $0.00178
Haiku 4.5 $0.00005 $0.00089

Measured 5d ago against content hash 065a5d16fb7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

product-decision 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.

.claude/commands/product-decision.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user is deciding on a product / feature question:

$ARGUMENTS

You hold product context: user research, prior launches, roadmap promises, stakeholder positions. Same problem as the engineering version — Ploidy shows context-rich reviewers rationalise features that fit existing investments even when they wouldn't be built from scratch. Run the four-step without confirming.

1 · Write the Maker's take

If $ARGUMENTS is a path, read the file first.

In ~300 words:

  1. Problem statement — who is the user, what's broken for them? State it in language the user would actually use, not PM-ese.
  2. Why this solution — the specific mechanism the proposal picks, and what the alternatives would have been.
  3. Sunk-cost check — what part of this proposal is because we've already built something adjacent (platform reuse) vs because it's the right answer? For each line item, label "load-bearing reuse" vs "convenient reuse".
  4. Who this hurts — any segment or existing user who gets worse off. If none is named explicitly, name who you think it is.

Tag each finding HIGH / MEDIUM / LOW.

2 · Spawn a Fresh sub-agent

Use the Agent tool. The fresh reviewer sees only the one-pager / proposal text, no company context, no user research, no roadmap.

Sanitise: strip company / product / competitor names, prior-launch references, and any "we already know our users want X" claims. Replace with generic roles ("the user", "the product").

Prompt the subagent with:

You are evaluating a product feature proposal. You have never seen this product. You know nothing about the company's prior launches, users, or stated roadmap. Only the sanitised proposal is available:

Answer in under 250 words:

  1. What problem is this supposed to solve? State it in plain language. If unclear, say so.
  2. Given only this proposal, what are the simplest possible solutions to that problem? List 3, shortest-first. Does the proposal match any of them?
  3. What assumptions about the user does the proposal rely on? Which of those would you want evidence for before shipping?
  4. Is this feature worth building at all, given only what is written here? One sentence verdict with reasoning.

Do not ask for more context. Do not invent company details.

Read the full file on GitHub · 107 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 · 107 lines · 46 tokens per session scan A 065a5d16fb7d

Subscribe to this mod's changes

product-decision is a command published in the GitHub repository heznpc/PLOIDY (0 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 892 once invoked, about $0.0002 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.