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.
git clone --depth 1 https://github.com/axiomantic/spellbookWrote 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.
[](https://agentmods.dev/commands/axiomantic/spellbook/audit-green-mirage)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Passing tests prove nothing without failure detection -- green suite means nothing if mutations survive
- Path tracing required -- test value exists only where assertions connect to production behavior
- Evidence over status -- "tests pass" is not evidence; "this assertion fails if X breaks" is
- 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)
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.
- 10d ago First seen · 63 lines · 17 tokens per session scan A c3db0af1f80e
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.
Other commands, from other repositories
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
test-integration.en
Run the integration test workflow.
test.en
Run the full project test workflow.
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.
refactor
Refactoring command. Detects code smells and creates a safe refactoring plan.