adversarial plugins

brandonsimpson/devils-advocate

Plugin Claude Code

Bundles 2 skills, 2 hooks · 24 tokens together

Claude's harshest critic. Evidence required. Perfection impossible.

liatrio-labs/claude-code-gauntlet

Plugin Claude Code

Bundles 3 skills, 12 agents, 1 hook · 733 tokens together

Adversarial code review for Claude Code: each GitHub PR or GitLab MR runs a gauntlet of up to seven specialist agents for bugs, security, tests and cross-file impact, and every finding must survive verification, a skeptical validator, and a blind challenge before it is posted.

serdardb/multi-agent

Plugin Claude Code

Bundles 2 skills, 3 agents · 197 tokens together

Run your OWN agent on other AI model CLIs (grok / codex / claude) as independent second opinions — no API, each model runs the agent natively. Two commands: /multi-agent (a single-model, live, steerable review you can talk to while it runs) and /arena (a deterministic multi-model adversarial arena — independent audit…

justinjdev/fight-club

Plugin Claude Code

Bundles 5 skills, 2 commands · 292 tokens together

Adversarial code review plugin. Fights bad code so your reviewers don't have to.