code-paper-test

Paper test code or skills with competing agent team (Happy Path + Edge Case + Red Team). Use when user says "test team", "3 perspectives", "competing testers", "thorough paper test", "security review", "deep code analysis", "test this skill with team". Best for large code (300+ lines), security-critical paths, or skill/command testing where perspective diversity matters most. For 50-300 line files, the single-agent structured 3-phase mode in /paper-test is more cost-effective. Each tester runs in isolated worktree.

Use when testing code, skills, commands, or configs through mental execution — trace logic line-by-line with concrete values to find bugs, logic errors, edge cases, contract violations, and AI hallucinations. Use when user says "paper test", "trace this", "find bugs", "check for edge cases", "audit this code", "verify AI code", "test this skill", "validate this implementation", "review this logic", "check dependencies", "check this config". MUST verify external calls — never assume methods exist. Use proactively before deploying changes or after AI generates code.

1 hook across 1 event