red-team-prd

red-team-prd is a command for Claude Code from phuryn/pm-skills. It costs 26 tokens per session (656 once invoked), scanned A, original, MIT.

A critical review of a product requirement document, roadmap, strategy, or other plan that tests the assumptions most important to its success. It identifies how those assumptions could fail and ranks the cheapest ways to check them.

In plain words
What is it for?
Use it to review a one-line business idea, product requirements, a roadmap, or a strategy memo and decide which claims to validate first.
Why use it?
It exposes weak points before time and money are committed. This helps teams test a risky idea early instead of discovering its failure after launch.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the pm-execution plugin — 16 skills, 11 commands shipped together

Good fit Use it to review a one-line business idea, product requirements, a roadmap, or a strategy memo and decide which claims to validate first.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/phuryn/pm-skills/red-team-prd
About the project

phuryn/pm-skills is a marketplace of reusable skills, commands, and plugins that guide AI assistants through product-management work such as discovery, strategy, planning, metrics, launches, and growth. It is for product managers and teams using Claude Code, Cowork, or compatible assistants. The catalogue entries are the project's own workflows and extensions.

phuryn/pm-skills · 26,131 stars · on GitHub · productcompass.pm

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/phuryn/pm-skills

Made for: Claude Code.

Or install pm-execution, the plugin that ships this one along with the rest of its 16 skills, 11 commands.

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 red-team-prd

README.md
[![agentmods](https://agentmods.dev/badge/commands/phuryn/pm-skills/red-team-prd/github.svg)](https://agentmods.dev/commands/phuryn/pm-skills/red-team-prd)
Your own site
<a href="https://agentmods.dev/commands/phuryn/pm-skills/red-team-prd"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/red-team-prd/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.

agentmods 80×15 button for red-team-prd

Your own site · 80×15
<a href="https://agentmods.dev/commands/phuryn/pm-skills/red-team-prd"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/red-team-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 656 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00656
Opus 5 $0.00013 $0.00328
Sonnet 5 $0.00005 $0.00131
Haiku 4.5 $0.00003 $0.00066

Measured 10d ago against content hash 016600f198a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

red-team-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 10d 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.

pm-execution/commands/red-team-prd.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/red-team-prd -- Attack the Plan Before Reality Does

Most plans only survived polite feedback. This command finds the assumptions that would make yours fail, attacks them honestly, and hands you the cheapest test for each — so you can kill a bad bet this week instead of at launch.

Invocation

/red-team-prd [paste or upload a PRD, roadmap, or strategy]
/red-team-prd Prioritize AI onboarding — activation is our bottleneck
/red-team-prd the current doc

Workflow

Step 1: Accept the Plan

Take it in any form — PRD, roadmap, strategy memo, one-line bet, or an uploaded doc. If the user says "the current doc," use the document in context.

Step 2: Red-Team It

Apply the strategy-red-team skill:

  • Extract every claim; keep only the load-bearing ones (false → plan dies).
  • Steelman each, then attack the steelman — no strawmen.
  • Write each failure mode as "Fails if ___."
  • Rank by (impact if wrong) × (likelihood wrong) × (cheapness to test).
  • Default "the risk is real" unless the plan cites evidence against it — but say plainly what's well-reasoned, and never fabricate a weakness.

Step 3: Return the Output

## Red-Team: [plan in one line]

### Top Kill-Assumptions (ranked)
- **Claim:** [load-bearing assertion]
  - **Fails if:** [concrete, falsifiable]
  - **Evidence to get this week:** [specific]
  - **Kill criterion:** [threshold]
  - **Cheapest test:** [smallest experiment]
[3–5 max]

### What's Well-Reasoned
[State it explicitly — don't manufacture doubt.]

### What I Couldn't Assess
[Where the plan didn't give enough to judge.]

Step 4: Offer Next Steps

  • "Want me to turn the top kill-assumption into an experiment you can run this week?"
  • "Should I run a pre-mortem to complement this — imagine it already failed and trace the path?"
  • "Want me to rewrite the riskiest section of the plan to address what survived?"

Notes

  • Lead with the ranking — the cheapest high-impact test is the whole point.
  • Five real kill-assumptions with tests beat twenty generic risks. Cut ruthlessly.
  • Distinct from /pre-mortem: pre-mortem narrates failure after the fact; red-team attacks the live assumptions and hands you the test.
  • If the plan is genuinely strong, the most valuable output is saying so — and naming the one thing still worth checking.
  • For a second-opinion pass, ask the user before adding cross-model friction; different model families miss different things, but most plans don't need it.

Read the full file on GitHub · 67 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. 10d ago First seen · 67 lines · 26 tokens per session scan A 016600f198a7

Subscribe to this mod's changes

red-team-prd is a command published in the GitHub repository phuryn/pm-skills (26,131 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 656 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 2026-08-30.