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-mirage-cross)<a href="https://agentmods.dev/commands/axiomantic/spellbook/audit-mirage-cross"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/audit-mirage-cross/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-mirage-cross"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/audit-mirage-cross.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 | $0.00015 | $0.00727 |
| Opus 5 | $0.00008 | $0.00364 |
| Sonnet 5 | $0.00003 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
audit-mirage-cross 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 4: Cross-Test Analysis
After auditing individual tests, analyze the suite as a whole.
Invariant Principles
- Coverage gaps matter more than individual test quality - A function with no test is a bigger risk than a function with a weak test
- Side-effect coverage is not direct coverage - A function exercised as a side effect of another test is not meaningfully tested
- Error paths deserve equal attention - Happy-path-only suites are the primary source of production incidents
Functions/Methods Never Tested
## Functions/Methods Never Tested
- module.function_a() - no direct test
- module.function_b() - only tested as side effect
Identify every public function/method in the production code that has NO direct test coverage. "Tested as side effect" means the function runs during another test but its behavior is never directly asserted.
Error Paths Never Tested
## Error Paths Never Tested
- What happens when X fails?
- What happens when Y returns None?
For each production function, enumerate the error branches (exceptions, null returns, timeout, invalid input) and check whether any test exercises that path.
Edge Cases Never Tested
## Edge Cases Never Tested
- Empty input
- Maximum size input
- Boundary values
- Concurrent access
Consider the domain-specific boundary conditions. What inputs sit at the edges of valid ranges? What about zero-length, max-length, negative, Unicode, or concurrent scenarios?
Skipped and Disabled Tests
## Skipped and Disabled Tests
- test_function_a - @skip("flaky") - UNJUSTIFIED (hides flakiness bug)
- test_function_b - @skipif(platform == 'darwin') - UNJUSTIFIED (macOS bug needs fixing)
- test_function_c - @skipif(platform != 'linux') - JUSTIFIED (linux-only kernel API)
- test_function_d - @xfail("race condition") - UNJUSTIFIED (known bug being ignored)
Scan the entire test suite for ALL skip mechanisms:
@pytest.mark.skip,@pytest.mark.skipif,@pytest.mark.xfail@unittest.skip,@unittest.skipIf,@unittest.skipUnless,@unittest.expectedFailurepytest.importorskip()callspytest.skip()called inside test bodies- Commented-out test functions (test code that was disabled rather than deleted)
- Conditional
returnat the start of test functions that silently exit
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 · 81 lines · 15 tokens per session scan A 930a9d7002e5
audit-mirage-cross is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 727 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.