Refines product specification documents by having multiple LLMs such as GPT, Gemini and Grok debate the draft until they reach consensus. Useful when a single model would miss gaps in a spec.
Claude Code
> /plugin marketplace add zscole/adversarial-spec> /plugin install adversarial-spec@adversarial-spec
Codex
$ npx skills add zscole/adversarial-spec -a codex
Cursor
$ npx skills add zscole/adversarial-spec -a cursor
Gemini CLI
$ npx skills add zscole/adversarial-spec -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add zscole/adversarial-spec$ copilot plugin install adversarial-spec@adversarial-spec
OpenCode
$ npx skills add zscole/adversarial-spec -a opencode
Windsurf
$ npx skills add zscole/adversarial-spec -a windsurf
A Claude Code plugin that iteratively refines product specifications through multi-model debate until consensus is reached.
Key insight: A single LLM reviewing a spec will miss things. Multiple LLMs debating a spec will catch gaps, challenge assumptions, and surface edge cases that any one model would overlook. The result is a document that has survived rigorous adversarial review.
Claude is an active participant, not just an orchestrator. Claude provides independent critiques, challenges opponent models, and contributes substantive improvements alongside external models.
# 1. Add the marketplace and install the plugin
claude plugin marketplace add zscole/adversarial-spec
claude plugin install adversarial-spec
# 2. Set at least one API key
export OPENAI_API_KEY="sk-..."
# Or use OpenRouter for access to multiple providers with one key
export OPENROUTER_API_KEY="sk-or-..."
# 3. Run it
/adversarial-spec "Build a rate limiter service with Redis backend"
You describe product --> Claude drafts spec --> Multiple LLMs critique in parallel
| |
| v
| Claude synthesizes + adds own critique
| |
| v
| Revise and repeat until ALL agree
| |
+--------------------------------------------->|
v
User review period
|
v
Final document output
litellm package: pip install litellm| Provider | Env Var | Example Models |
|---|---|---|
| OpenAI | OPENAI_API_KEY | gpt-4o, gpt-4-turbo, o1 |
| Anthropic | ANTHROPIC_API_KEY | claude-sonnet-4-20250514, claude-opus-4-20250514 |
GEMINI_API_KEY | gemini/gemini-2.0-flash, gemini/gemini-pro | |
| xAI | XAI_API_KEY | xai/grok-3, xai/grok-beta |
| Mistral | MISTRAL_API_KEY | mistral/mistral-large, mistral/codestral |
| Groq | GROQ_API_KEY | groq/llama-3.3-70b-versatile |
| OpenRouter | OPENROUTER_API_KEY | openrouter/openai/gpt-4o, openrouter/anthropic/claude-3.5-sonnet |
| Codex CLI | ChatGPT subscription | codex/gpt-5.2-codex, codex/gpt-5.1-codex-max |
| Gemini CLI | Google account | gemini-cli/gemini-3-pro-preview, gemini-cli/gemini-3-flash-preview |
| Deepseek | DEEPSEEK_API_KEY | deepseek/deepseek-chat |
| Zhipu | ZHIPUAI_API_KEY | zhipu/glm-4, zhipu/glm-4-plus |
Check which keys are configured:
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" providers
For enterprise users who need to route all model calls through AWS Bedrock (e.g., for security compliance or inference gateway requirements):
# Enable Bedrock mode
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" bedrock enable --region us-east-1
# Add models enabled in your Bedrock account
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" bedrock add-model claude-3-sonnet
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" bedrock add-model claude-3-haiku
# Check configuration
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" bedrock status
# Disable Bedrock mode
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" bedrock disable
When Bedrock is enabled, all model calls route through Bedrock - no direct API calls are made. Use friendly names like claude-3-sonnet which are automatically mapped to Bedrock model IDs.
Configuration is stored at ~/.claude/adversarial-spec/config.json.
OpenRouter provides unified access to multiple LLM providers through a single API. This is useful for:
Setup:
# Get your API key from https://openrouter.ai/keys
export OPENROUTER_API_KEY="sk-or-..."
# Use OpenRouter models (prefix with openrouter/)
python3 debate.py critique --models openrouter/openai/gpt-4o,openrouter/anthropic/claude-3.5-sonnet < spec.md
Popular OpenRouter models:
openrouter/openai/gpt-4o - GPT-4o via OpenRouteropenrouter/anthropic/claude-3.5-sonnet - Claude 3.5 Sonnetopenrouter/google/gemini-2.0-flash - Gemini 2.0 Flashopenrouter/meta-llama/llama-3.3-70b-instruct - Llama 3.3 70Bopenrouter/qwen/qwen-2.5-72b-instruct - Qwen 2.5 72BSee the full model list at openrouter.ai/models.
Codex CLI allows ChatGPT Pro subscribers to use OpenAI models without separate API credits. Models prefixed with codex/ are routed through the Codex CLI.
Setup:
# Install Codex CLI (requires ChatGPT Pro subscription)
npm install -g @openai/codex
# Use Codex models (prefix with codex/)
python3 debate.py critique --models codex/gpt-5.2-codex,gemini/gemini-2.0-flash < spec.md
Reasoning effort:
Control how much thinking time the model uses with --codex-reasoning:
# Available levels: low, medium, high, xhigh (default: xhigh)
python3 debate.py critique --models codex/gpt-5.2-codex --codex-reasoning high < spec.md
Higher reasoning effort produces more thorough analysis but uses more tokens.
Available Codex models:
codex/gpt-5.2-codex - GPT-5.2 via Codex CLIcodex/gpt-5.1-codex-max - GPT-5.1 Max via Codex CLICheck Codex CLI installation status:
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" providers
Gemini CLI allows Google account holders to use Gemini models without separate API credits. Models prefixed with gemini-cli/ are routed through the Gemini CLI.
Setup:
# Install Gemini CLI
npm install -g @google/gemini-cli && gemini auth
# Use Gemini CLI models (prefix with gemini-cli/)
python3 debate.py critique --models gemini-cli/gemini-3-pro-preview < spec.md
Available Gemini CLI models:
gemini-cli/gemini-3-pro-preview - Gemini 3 Pro via CLIgemini-cli/gemini-3-flash-preview - Gemini 3 Flash via CLICheck Gemini CLI installation status:
python3 "$(find ~/.claude -name debate.py -path '*adversarial-spec*' 2>/dev/null | head -1)" providers
For models that expose an OpenAI-compatible API (local LLMs, self-hosted models, alternative providers), set OPENAI_API_BASE:
# Point to a custom endpoint
export OPENAI_API_KEY="your-key"
export OPENAI_API_BASE="https://your-endpoint.com/v1"
# Use with any model name
python3 debate.py critique --models gpt-4o < spec.md
This works with:
Start from scratch:
/adversarial-spec "Build a rate limiter service with Redis backend"
Refine an existing document:
/adversarial-spec ./docs/my-spec.md
You will be prompted for:
gpt-4o,gemini/gemini-2.0-flash,xai/grok-3)More models = more perspectives = stricter convergence.
For stakeholders, PMs, and designers.
Sections: Executive Summary, Problem Statement, Target Users/Personas, User Stories, Functional Requirements, Non-Functional Requirements, Success Metrics, Scope (In/Out), Dependencies, Risks
Critique focuses on: Clear problem definition, well-defined personas, measurable success criteria, explicit scope boundaries, no technical implementation details
For developers and architects.
Sections: Overview, Goals/Non-Goals, System Architecture, Component Design, API Design (full schemas), Data Models, Infrastructure, Security, Error Handling, Performance/SLAs, Observability, Testing Strategy, Deployment Strategy
Critique focuses on: Complete API contracts, data model coverage, security threat mitigation, error handling, specific performance targets, no ambiguity for engineers
Before the debate begins, opt into an in-depth interview session to capture requirements upfront.
Covers: Problem context, users/stakeholders, functional requirements, technical constraints, UI/UX, tradeoffs, risks, success criteria
The interview uses probing follow-up questions and challenges assumptions. After completion, Claude synthesizes answers into a complete spec before starting the adversarial debate.
Each round, Claude:
Display format:
--- Round N ---
Opponent Models:
- [GPT-4o]: critiqued: missing rate limit config
- [Gemini]: agreed
Claude's Critique:
Security section lacks input validation strategy. Adding OWASP top 10 coverage.
Synthesis:
- Accepted from GPT-4o: rate limit configuration
- Added by Claude: input validation, OWASP coverage
- Rejected: none
If a model agrees within the first 2 rounds, Claude is skeptical. The model is pressed to:
This prevents false convergence from models that rubber-stamp without thorough review.
After all models agree, you enter a review period with three options:
Run multiple cycles with different strategies:
Stars on GitHub
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraHelps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookRefines product specification documents by having multiple LLMs such as GPT, Gemini and Grok debate the draft until they reach consensus. Useful when a single model would miss gaps in a spec. Install it with the command on its page. It includes adversarial-spec. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it