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.
npx skills add CATWILLgh/MAINFRAME --skill mainframe-test-auditgit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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/skills/catwillgh/mainframe/mainframe-test-audit)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-test-audit"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-test-audit/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/skills/catwillgh/mainframe/mainframe-test-audit"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-test-audit.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 | $0.00076 | $0.01023 |
| Opus 5 | $0.00038 | $0.00511 |
| Sonnet 5 | $0.00015 | $0.00205 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
mainframe-test-audit 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 2d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-system audit
Apply this method when the active work matches the description, whether you are the primary auditor or a delegated specialist. Follow the scope and authority supplied through the current execution path; this skill does not expand either.
Audit the existing test system rather than redesigning it from preference. Tests protect observable guarantees, not a target count, coverage percentage, framework fashion, or universal ratio of test levels.
Establish the audit boundary
Identify the exact package, component, journey, test layer, suite, or execution contour under review. State the observable product guarantees inside that boundary and the concrete regressions the tests are expected to detect.
Inspect the effective project instructions, relevant product decisions and contracts, owning code paths, test configuration, existing tests, fixtures and lifecycle setup, native commands, and applicable CI configuration. Do not broaden a bounded audit into a repository-wide review.
Map how the project obtains each kind of evidence:
- focused checks used while changing one behavior;
- the nearest fast local regression suite;
- checks whose correctness depends on a real local dependency;
- broad, compatibility, deployed, or full-system checks reserved for CI or a deliberately prepared environment.
The absence of one universal test command is not a defect. Judge whether the applicable checks can be discovered, understood, and rerun without unrelated infrastructure or hidden side effects.
Test the quality of the evidence
For every material guarantee, identify the cheapest observation that would faithfully fail for the real regression. Inspect whether the current evidence:
- reaches the behavior through the boundary where the defect can occur;
- asserts an observable contract strongly enough to detect the failure;
- uses a mock, stub, emulator, database substitute, or fixture that preserves the relevant semantics;
- avoids coupling to private implementation details that can change without changing behavior;
- covers only branches that actually exist, without duplicating the same guarantee for ceremony;
- isolates time, randomness, ordering, process state, shared data, network access, and concurrency sufficiently to be repeatable;
- makes setup, infrastructure, runtime, and maintenance cost visible and proportional to the risk.
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.
- 2d ago First seen · 65 lines · 76 tokens per session scan A 651372d467e6
mainframe-test-audit is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,023 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
prompt-eval-builder
Domain knowledge for extracting eval assertions and generating test invocation prompts from command/agent specs. Used for building promptfoo evaluation configs.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).
eval-harness
Assessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.
code-check
Fast code hygiene validation (lints, formatters, tests, coverage) for quick development loop feedback.
ph-grill-me
(PH) Pressure-test a concrete decision, design, or plan only when the user asks to examine assumptions, alternatives, risks, or trade-offs.