Adversarial Spec
Multiple AI models critique a spec/PRD until consensus. GPT, Gemini, Grok each find different weaknesses. Iterates until all models agree the spec is solid. Use for critical project specifications.
Install
$ agentstack add skill-neuron-one-godmode-adversarial-spec ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Adversarial Specification Review
Process
- Send spec to 2-3 different models simultaneously
- Each model critiques independently
- Claude collects all criticism
- Claude rewrites spec addressing all points
- Send revised spec back to models
- Repeat until consensus
What Models Check
- Missing requirements
- Ambiguous language
- Scope creep indicators
- Security gaps
- Performance blind spots
- Edge cases not covered
Consensus Rules
- If a model agrees too quickly -> force it to prove it read the document
- Minimum 2 rounds of critique
- Final spec must address ALL raised issues
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: neuron-one
- Source: neuron-one/GODMODE
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.