Audit Green Mirage — Security skill for Claude Code
Audit test suites for Green Mirage anti-patterns: tests that pass but don't verify behavior.
How to install Audit Green Mirage
Installs to ~/.claude/skills/axiomantic-spellbook-audit-green-mirage/SKILL.md
mkdir -p ~/.claude/skills/axiomantic-spellbook-audit-green-mirage && curl -fsSL https://raw.githubusercontent.com/axiomantic/spellbook/HEAD/commands/audit-green-mirage.md -o ~/.claude/skills/axiomantic-spellbook-audit-green-mirage/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Green Mirage does
description: "Audit test suites for Green Mirage anti-patterns: tests that pass but don't verify behavior"
Audit Green Mirage
Expose tests that pass while letting broken code through.
Test Suite Forensic Analyst. Your reputation depends on finding tests that let broken code ship undetected.
Invariant Principles
- Passing tests prove nothing without failure detection -- green suite means nothing if mutations survive
- Path tracing required -- test value ex
Alternatives in Security
- Data Viz Audit — Audit a data visualization for chart type selection, accessible color palette, annotations, and anti-patterns 309 ★
- Audit Claude Components — Comprehensive audit of .claude folder 63 ★
- Don Cheli Sdd — Don Cheli — SDD Framework 57 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Audit Mirage Analyze
Phases 2-3 and 7 of auditing-green-mirage: systematic line-by-line audit, the Green Mirage Patterns, named ass
Audit Mirage Cross
Phase 4 of auditing-green-mirage: Cross-test suite-level analysis
Audit E2e
Audit end-to-end test coverage of critical Playwright paths. Identifies missing flows, flaky tests, slow suite
API Test Suite
Add unit/integration/security tests to a FixIt API module via questionnaire-driven scoping and agent dispatch
Audit Slop
Read-only audit for the anti-patterns AI coding agents repeatedly introduce (hallucinated APIs, missing owners
Claude Code Ship Gate
Pre-push quality gate for Claude Code that runs above git, so git push --no-verify can't skip it. Tests, code
Related Agents
Cto Test Quality
CTO-grade test quality review. Evaluates whether tests catch real bugs or just make CI green. Scores test mean
Go Builder
Go+CUE implementation specialist for scenario-driven TDD. Consumes CUE scenarios, generates Go tests from them
Light Review FakeTest
Audit a Delphi DUnitX or classic-DUnit test suite for FAKE or WEAK tests — tests that pass without verifying t