# Adversarial Code Review Tdd

> Systematic adversarial review pattern to identify breaking assumptions in already-passing test suites

- Skill: `vamseeachanta/adversarial-code-review-tdd` (Agent Skill)
- Install (CLI): `npx skillmds@latest add vamseeachanta/adversarial-code-review-tdd`
- Raw SKILL.md: https://api.skillmd.com/api/skills/vamseeachanta/adversarial-code-review-tdd/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: vamseeachanta (https://skillmd.com/u/vamseeachanta)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/vamseeachanta/adversarial-code-review-tdd

---


# Adversarial Code Review for Passing Tests

When tests pass but implementation may have hidden flaws, conduct adversarial review by: (1) identify sentinel values or default parameters that conflate different states (e.g., `decline_rate=0.0` as both "not set" and "valid input"), (2) check boundary conditions for unjustified constraints (e.g., `b_factor < 1` when b=1 is mathematically valid), (3) distinguish between user intent and implementation convenience. Fix MAJOR findings, add regression tests for edge cases, then re-run full suite before committing.