- Home
- Skills
- Code Quality & Review
- Adversarial Code Review: Findings Need a Failing Test
Works with the AI Agents you already use
Adversarial Code Review: Findings Need a Failing Test
Free review pass that attacks the change like a hostile tester and only reports what it can prove.
Free
About this skill
A reviewer whose job is to break the change, not approve it. It walks 9 attack-surface categories (races, idempotency and retries, partial failure, boundaries, money and numbers, time, security, error handling, resources). A finding only counts when a failing test reproduces it.
- Ends in GATE PASS or GATE FAIL, so it can't rubber-stamp.
- REVIEW template with severity, evidence and verdict.
- No failing test, no finding.
Free. For a deeper, benchmarked review use Proven Code Review.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
3 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 28 days ago
- Free with an Agensi account
Permissions
No special permissions declared or detected