Agent Claude Code
Execute exactly one agent-infra lifecycle stage in a fresh context.
not rated 86 today A 21 tokens
original MIT
6 tagged ai-collaboration, measured the same way as everything else here.
Browse within: best-practices 10coding-standards 10commit-conventions 10cli 6
Agent Claude Code
Execute exactly one agent-infra lifecycle stage in a fresh context.
Agent Claude Code
An adversarial review agent for testing conclusions or proposed fixes that already have supporting evidence. It tries to disprove the recommended action with counterexamples and checks whether the proposed fallback repeats the original problem.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: