audit-green-mirage

audit-green-mirage is a command for Claude Code from axiomantic/spellbook. It costs 17 tokens per session (549 once invoked), scanned A, original, MIT.

A test-suite audit that finds tests which pass without checking whether the code actually behaves correctly.

In plain words
What is it for?
Use it to inspect test files, trace tests to production code, identify weak failure checks, and produce file-and-line fixes.
Why use it?
It helps expose false confidence from weak assertions, unverified mocks, and coverage that only shows code ran. It also checks whether tests would catch deliberate code changes.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to inspect test files, trace tests to production code, identify weak failure checks, and produce file-and-line fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/audit-green-mirage
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for audit-green-mirage

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/audit-green-mirage/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/audit-green-mirage)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/audit-green-mirage"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/audit-green-mirage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-green-mirage

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/audit-green-mirage"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/audit-green-mirage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00549
Opus 5 $0.00009 $0.00275
Sonnet 5 $0.00003 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 10d ago against content hash c3db0af1f80e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-green-mirage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/audit-green-mirage.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

  1. Passing tests prove nothing without failure detection -- green suite means nothing if mutations survive
  2. Path tracing required -- test value exists only where assertions connect to production behavior
  3. Evidence over status -- "tests pass" is not evidence; "this assertion fails if X breaks" is
  4. Mirages hide in coverage gaps -- high coverage with weak assertions creates false confidence

Execution

Skill performs:

  • Discover all test files
  • Trace paths: test -> assertion -> production code
  • Identify anti-patterns (weak assertions, missing failure modes, coverage without verification)
  • Generate findings with exact fixes (file, line, specific change)

Mutation analysis: run or simulate code mutations to verify assertions would catch them; a test that passes with production code deleted is not a test.

Anti-patterns to Detect

  • Assertions without failure conditions
  • Mocks that never verify calls
  • Coverage from execution, not verification
  • Happy-path-only tests
  • Tests that pass when production code deleted
  • Skipped, xfailed, or disabled tests hiding real failures (a test that never runs catches zero bugs)

Read the full file on GitHub · 63 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 63 lines · 17 tokens per session scan A c3db0af1f80e

Subscribe to this mod's changes

audit-green-mirage is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 549 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.