adversarial-plan-review

Name: adversarial-plan-review
Availability: InStock
Author: smp4

Coordinate persona subagents to adversarially review plan and spec documents.

Updated Mar 2, 2026

Search Tags:#subagents #claude-code #multi-persona #adversarial-review #plan-analysis #risk-identification #synthesis-prompt

Ready to run

npx skills add https://github.com/smp4/claude-skills --skill adversarial-plan-review

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: adversarial-plan-review
Source: https://github.com/smp4/claude-skills/tree/main/docs/dev/ideas/personas/persona-skills-context/adversarial-plan-review
Command: npx skills add https://github.com/smp4/claude-skills --skill adversarial-plan-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill ensures major plans undergo honest, independent critique so hidden risks, assumptions, and irreversible bets in plan.md or spec.md documents are surfaced before committing to implementation.

Core Features & Use Cases

Structured reviewer panel keeps Ford + Parsons, Kua, Farley, and Feathers focused on evolvability, reversibility, releasability, and testability while collecting their raw, persona-specific findings.
Parallel subagents run in isolation as described in the references, preventing anchoring and speeding up review of lengthy documents.
Use Case: After /new-plan creates SPEC.md, run this workflow to catch architecture or process hazards, then feed the collected insights into the human synthesis questions before proceeding.

Quick Start

Run the adversarial-plan-review skill on SPEC.md with the default panel to collect reviewer outputs and a synthesis prompt.

Frequently Asked Questions about adversarial-plan-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run an adversarial review on a plan.md or spec.md document?▼

The review uses a structured panel including Ford + Parsons, Kua, Farley, and Feathers personas, each focused on specific dimensions like evolvability, reversibility, releasability, or testability. They collect raw findings independently before synthesis.

What's the best way to stress-test a spec for hidden risks before committing to implementation?▼

Stress-test a spec by running parallel subagent reviews in isolation across multiple dimensions, then gather every finding and identify cross-cutting patterns. The workflow presents synthesis questions for human decisions before you proceed.

How does multi-persona adversarial plan analysis work with subagents?▼

Multi-persona adversarial analysis works by assigning isolated subagents distinct reviewer personas that independently evaluate the verbatim plan text. This prevents anchoring and speeds up review of lengthy documents before findings are collected and synthesized.

Can I use adversarial-plan-review with claude-code for multi-persona risk identification?▼

Yes, the adversarial-plan-review skill coordinates multiple persona subagents within claude-code to perform risk identification on your plan. It requires no external dependencies and uses subagent isolation to ensure independent reviews.

When do I need to run an adversarial review on my architecture plan?▼

You need an adversarial review after creating a SPEC.md or plan.md and before committing to implementation. It surfaces hidden risks, assumptions, and irreversible bets in your architecture or process documents.

What are the limitations of using isolated subagents for plan analysis?▼

A limitation of isolated subagent plan analysis is that reviewers cannot cross-reference each other's findings during the initial review phase. Cross-cutting patterns are only identified after all isolated reviews are gathered and synthesized into human decision questions.