Skip to main content
command CX Codex

red-team-prd — Claude Code command: test assumptions before launch

The red-team-prd command for Claude Code extracts and challenges assumptions that could break a plan, then suggests the cheapest test for each.

MIT ★ 28,211 updated 2026-10-16

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add phuryn/pm-skills
/plugin install pm-execution@pm-skills
Open on GitHub

What red-team-prd does

Most plans survive only polite critique. red-team-prd takes a PRD, roadmap, or strategy, extracts the load-bearing assumptions, and ranks them by impact if wrong, likelihood of error, and cost to test. The output is a prioritised list of kill-assumptions with a specific, cheap experiment for each.

Accepts text, file upload, or a single phrase. Say "the current doc" and it uses context from your document. Different from /pre-mortem because pre-mortem narrates failure in hindsight; red-team attacks live assumptions and hands you the test worth running this week.

After analysis, it offers next steps: turn the top kill-assumption into an experiment, run a complementary pre-mortem, or rewrite the riskiest section of your plan.

What it helps with

  • Identify which assumptions would kill your plan if wrong
  • Find the cheapest experiment to validate each bet
  • Separate well-reasoned parts of your strategy from risky ones
  • Rank threats by actual danger, not how urgent they sound
  • Catch a bad assumption before it costs you months

Example prompts for the agent

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

How to install red-team-prd

1Plugin marketplace

/plugin marketplace add phuryn/pm-skills
/plugin install pm-execution@pm-skills

2Manually: put the files in place

.claude/commands/red-team-prd.md

Call it with /red-team-prd. For all projects use ~/.claude/commands/

Questions about red-team-prd

How do I install red-team-prd in Claude Code?

Run /plugin marketplace add phuryn/pm-skills, then /plugin install pm-execution@pm-skills. The command is also available in .claude/commands/red-team-prd.md.

What does red-team-prd do?

It identifies load-bearing assumptions in your plan — the ones where being wrong kills the whole thing — and ranks them by impact, likelihood of error, and test cost. Each gets a specific, cheap experiment.

How is red-team-prd different from pre-mortem?

Pre-mortem narrates failure after the fact; you imagine the project already failed and trace back. Red-team attacks live assumptions and gives you the test you can run this week to validate or kill a bet right now.

Source text

red-team-prd.md · MIT
---
description: Red-team a PRD, roadmap, or strategy — attack its load-bearing assumptions and return the cheapest test for each before you commit
argument-hint: "<PRD, roadmap, strategy, or the current doc>"
---

# /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.

© Paweł Huryn · MIT · phuryn/pm-skills

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set120

The whole set →
proofread proofread is a Claude Code command that checks grammar, reasoning, and flow in pasted or uploaded text, suggesting focused fixes for drafts, documents, and emails. CX Codex +1 ★ 28,211repo stars draft-nda The draft-nda command creates professional Non-Disclosure Agreements tailored to your jurisdiction, parties, and scope of information. CX Codex +1 ★ 28,211repo stars privacy-policy Drafts a privacy policy tailored to GDPR and CCPA, complete with compliance checklists and flags for legal review. Useful when launching new apps and web tools. CX Codex +1 ★ 28,211repo stars tailor-resume tailor-resume matches a resume to a target job description by aligning terms, reframing experience, and exposing gaps before an application. CX Codex +1 ★ 28,211repo stars generate-data generate-data generates realistic mock datasets in CSV, JSON, or SQL using Python scripts with custom distributions and constraints. CX Codex +1 ★ 28,211repo stars write-query write-query turns plain language descriptions into SQL queries across BigQuery, PostgreSQL, MySQL and other dialects. Upload a schema or describe your tables, then ask your question. CX Codex +1 ★ 28,211repo stars value-proposition value-proposition maps a product or feature to a six-part template: target user, their job, current friction, your solution, resulting outcome, and why you beat alternatives. CX Codex +1 ★ 28,211repo stars test-scenarios Turns user stories and feature specifications into structured test scenarios covering happy paths, edge cases, and errors. CX Codex +1 ★ 28,211repo stars

Project sponsors

Companies that keep this analytics open