Skill Claude CodeCodex
A multi-reviewer process that sends an important conclusion or design to three independent critics: a skeptic, a security reviewer, and a simplifier.
Make Claude Code work like a disciplined engineer: OODA, multi-party adversarial review, tiered model routing, fail-then-pass — token-efficient by design (route heavy work to smaller models, isolate sub-agent context). Distilled from Fable to reinforce the Opus harness.
Skill Claude CodeCodex
A multi-reviewer process that sends an important conclusion or design to three independent critics: a skeptic, a security reviewer, and a simplifier.
Skill Claude CodeCodex
Decision rules for coding agents about when to slow down, ask the user, change approach, or perform a final challenge of their own solution. They focus on risky changes, repeated failures, secrets, and complex state or timing behavior.
Skill Claude CodeCodex
Rules for assigning coding and exploration work to helper agents. They define what the assignment must contain, when to delegate, which model level to use, and how results should be reported.