Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsAdversarial Review Gate: every finding needs a failing test
A code review that tries to break the change: findings count only with a failing test that reproduces them, ending in GATE: PASS or GATE: FAIL.
Free
About this skill
A code review that tries to break the change instead of approving it. Each finding must come with a failing test that reproduces it, and the review ends GATE: PASS or GATE: FAIL; "looks good" is not an outcome.
Ships a nine-category attack checklist (races, idempotency, partial failure, boundaries, money, time, security, error mapping, resources), a report template, and a real case study in which the gate caught a lock-timeout bug that a thread-storm test missed.
Built for reviewing AI-generated code. Part of the agent-forge pipeline (github.com/Ces107/agent-forge).
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean today
- Free to download with an account