Adversarial Spec
Iteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and other models. Includes interview mode, early agreement verification, and optional Telegram integration.
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Productivity — see all ranked ›
Work: PRDs and specs
Who it is for: Product manager · Software engineer
“Model table with env vars per provider; every CLI call needs a find-the-script call.”
- tashan score: 52.0
- Expertise: 79.0 (solid)
- Adoption: 1 repos
- Health: stable
- GitHub stars: 554
- Contributors: 6
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:zscole/adversarial-spec/adversarial-spec
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›