challenger

PackAI & models

Puts four critic agents against your coding decisions to find weak spots before you commit.

Unavailable. Delivery for this kind is on the roadmap — not serving yet.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

About this app

Multi-agent adversarial plugin that stress-tests code decisions, architecture plans, and reasoning through evidence-backed challenge rounds. Four specialized agents (Skeptic, Sentinel, Architect, Pragmatist) take turns poking holes in your conclusions using actual codebase evidence, reading code, s

Signals

GitHub stars
4k
Forks
312
Last commit
Aug 2026
Advanced
Item type
plugin
Key
anthropics-claude-plugins-community-challenger
Source
github.com/anthropics/claude-plugins-community