Protocol Enforcement (Red-Team Verification)

Priority: P0 (CRITICAL)

Red-Team Verification Protocol

Before declaring any task "done" or calling notify_user:

1. Adversarial Audit: Search for Standard Defaults where project rules should exist.
2. Protocol Check: Confirm active skills and workflows were loaded before writing.
3. Evidence Check: Ask what observable command or artifact proves the completion claim.
4. Execution Bias Check: Ask whether speed or convenience skipped a structural rule.

Risk-Based Post-Write Self-Scan

Trigger a post-write self-scan under specific risk or freshness conditions:

• Condition: State freshness is uncertain, external modifications occurred, tool output indicated partial edits or conflicts, or changes touch sensitive paths (auth, security, payments, data integrity).
• Scan: Inspect the diff or touched section rather than ritualistic re-reading of entire files.
• Match: Check against Anti-Patterns in all active skills.
• Fix: Re-edit immediately if a violation is detected.

Red Flags

• Stop if "done" appears before fresh verification: Require observable evidence (test output, diff check, diagnostic artifact).
• Stop if assuming stale file state is intact: Verify source of truth when freshness is uncertain or tools signal ambiguity.
• Stop if the shortcut is "small enough to skip protocol": Small changes hide drift.

Rationalization Prevention

• "The change is tiny": Tiny changes still violate guardrails.
• "The test passed earlier": Old evidence does not prove current state.
• "I know the pattern already": Verify active project rules anyway.

Anti-Patterns