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 | $0.00050 | $0.01378 |
| Opus 5.5 | $0.00020 | $0.00551 |
| Sonnet 5.5 | $0.00010 | $0.00276 |
| Haiku 4.5 | $0.00005 | $0.00138 |
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 26d 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 — 75 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.
Apply the same standard from the audit side
mainframe-testing owns the shared testing and CI criteria. Use its relevant reference as an evaluation standard, not as authority to implement: references/strategy.md for the shared test-level selection and project verification map, references/tooling.md for analyzer selection, reuse and execution boundaries, behavior/TDD for regression sensitivity, local boundaries for fixtures and infrastructure, and CI plus the applicable GitHub/GitLab reference for triggers, required results, trust and cost. Read only the branch needed by the audited risk; keep shared policy there rather than maintaining a second version here. If unavailable, report that limitation and continue the evidence-backed audit that remains possible.
Mirror the implementation guarantees in the findings: behavior is actually observed; relevant defects make the check fail; fixtures preserve the claimed semantics and remain isolated; local work respects the lightweight/verified PostgreSQL boundary; required CI work runs for the correct revision and event; green results and cost claims have supporting evidence. Do not infer missing TDD history from the current files or demand reconstruction of every historical red run.
Apply this method proactively when a concrete test-system concern falls within the current assignment, not for every ordinary regression run. Its result is supported findings and acceptance conditions, not edited tests or a product readiness verdict. Use mainframe-testing for authorized creation or repair. When the caller already assigned audit and repair, separate the read-only investigation from implementation without asking again for supplied authority; a delegated audit-only role returns findings and retains its boundary.
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.
- 26d ago Changed · +10 lines · +17 tokens per session 63de86587be9
- 1mo ago Changed · -43 tokens per session d5b943fc072b
- 1mo 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 10d ago), licensed MIT. It adds 50 tokens to every session and 1,378 once invoked, about $0.0002 per session on Opus 5.5. 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
ralph
Self-referential loop until task completion with configurable verification reviewer.
test-value
Improve test value and feedback cost when auditing slow, flaky, redundant or brittle tests; choosing tests during implementation; or reviewing test changes before a commit or PR. Keep ordinary implementation and pre-commit use scoped to the affected behavior, not a repository-wide audit.
tdd
Test-first at pre-agreed seams — one test, one implementation, tracer-bullet red/green; independent expected values; substitutions only at the seam's boundary class; launch Phase 4 reference.
horizon-device
Manage Horizon native VNC Device panels and drive isolated local desktops for simulators and native application tests through devicepanel and the horizon-device CLI/MCP. Device panels work on every platform; driving an isolated desktop works on Linux with X11 only. Browser pages use horizon-browser.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right or follows the…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests, including junk tests (prose pins, source greps, copied inventories, mock echoes), each proven by its class's rule before a cut. Use when the user asks to clean up, deslop, remove AI-slop patterns, or prune tests from…