Red Team

Overview

All subagent dispatches use disk-mediated dispatch. See shared/dispatch-convention.md for the full protocol.

Adversarial review of any artifact. Dispatches a Devil's Advocate subagent to attack the work, fixes findings, then dispatches a FRESH Devil's Advocate to attack again. Iterates until clean or stagnation is detected.

Core principle: Fresh eyes every round. No anchoring, no confirmation bias.

Announce at start: "I'm using the red-team skill to adversarially review this artifact."

Skill Arguments (added by #303)

Argument	Type	Default	Effect
`cost_cap_threshold`	int \| null	`3` if `suppression_threshold > 3` else `null` (auto-null on hypothesis/mockup/translation defaults)	Standalone-mode only: LOCAL round at which the cost-cap prompt fires (interactive only). Set to `null` to disable.
`dr_signal_findings`	int \| null	`2` if `suppression_threshold > 3` else `null`	Standalone-mode only: count of NEW (delta-vs-prior-round) Fatal+Significant findings at or below which the DR signal fires (interactive only).