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
/plugin marketplace add phuryn/pm-skills
/plugin install pm-execution@pm-skillsWhat 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-skills2Manually: put the files in place
.claude/commands/red-team-prd.mdCall it with /red-team-prd. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/red-team-prd.mdCall it with /prompts:red-team-prd. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/red-team-prd.prompt.mdManually: put the files in place
.gemini/commands/red-team-prd.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
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