Agent Code Quality Suite — Judge, Review & Ship Safer Code
Three gates that make AI-written code safe to ship. evidence-guard audits docs, READMEs, and technical claims for anything unsupported; the Peer-Review Stress Test makes your agent its own harshest reviewer, hunting overclaims and missing limitations; and the Coding Agent Quality Gate runs a senior-engineer pre-ship review of the diff for correctness gaps, missing error handling, security anti-patterns, and untested edge cases — returning one clear SHIP/REVISE/BLOCK verdict. Built for developers using Claude Code, Cursor, Codex CLI, and any SKILL.md-compatible agent. Buy all three together and save 30%.
You save $15 vs buying individually.
What's included (3 skills)
An adversarial self-review gate that hunts your agent's weakest claim, overclaims, and missing limitations before a human sees the output.
An adversarial senior engineer review gate that audits AI-written code for security gaps and logic errors before shipping.
Audit any AI-generated output for unsupported claims, then verify every factual and technical assertion against its real source before it ships.