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-testinggit 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-testing)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-testing"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-testing/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-testing"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-testing.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 | $0.00058 | $0.01089 |
| Opus 5.5 | $0.00023 | $0.00436 |
| Sonnet 5.5 | $0.00012 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
mainframe-testing 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 9d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Own the behavior and its verification
Apply this method as the primary agent or a delegated engineer within the same task authority. Use the stack-specific engineering skill for native tools and contracts. This method does not authorize implementation during read-only investigation or verification, global installation, remote access, publication, or deployment.
For a behavior change, use test-driven development: demonstrate the relevant failing behavior before the fix, implement the smallest complete correction, then refactor while the focused checks remain green. A compiler, import, setup, credential, or network failure is not the intended red result. Reuse an existing test that already demonstrates the defect; do not add a duplicate solely to claim TDD.
State what observable behavior must change, what must remain true, and which boundary can prove it. Test user-visible results and protected side effects rather than private implementation details. Include meaningful rejection, boundary, failure, retry, concurrency, and cleanup cases when the contract contains them; do not generate an indiscriminate test matrix.
Choose the operation
Use this method proactively when implementation requires tests, test changes, or CI work; an explicit request to “use TDD” is unnecessary. It owns how verification is built and run, including ordinary regression checks after a change. Its result is the authorized change with meaningful tests and accurately bounded evidence.
Use mainframe-test-audit when the task is to assess the quality of an existing test system, or concrete escaped regressions, flakiness, misleading green results, or measured cost warrant investigation within scope. That method evaluates the same criteria without changing the audited system. Do not start an audit for every test run or load both full methods by default.
For an assignment that includes both audit and repair, keep findings and implementation as explicit phases and reuse the caller's existing repair authority. A delegated read-only auditor returns findings to its caller; it does not become an implementer. An author may review their own work but must not claim an independent audit.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 47 lines · 58 tokens per session scan A 956f0b918d98
mainframe-testing is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 1,089 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 2026-10-07.
Other skills, from other repositories
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.
setup
Set up or update TDD Guard for the current project. Detects the test framework, installs or updates the matching reporter, and configures or migrates its configuration to match the current specification.
cicd-pipeline-qe-orchestrator
Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing.
subagent-testing
Test skills via TDD in fresh subagents. Use when validating behavior or preventing bias.
cmux-testing
Choose scoped cmux verification, add behavioral tests, and validate Swift test targets and wiring. Use when adding tests or deciding what local/CI evidence a change needs.
tdd-ask-help
Interactive AI Guide and Navigator for the TDD-Spec SDLC ecosystem. Diagnoses current project phase, recommends next actions, routes scenarios, and explains skill purposes.