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 agentmods add skills/catwillgh/mainframe/mainframe-testing-strategynpx skills add CATWILLgh/MAINFRAME --skill mainframe-testing-strategygit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWhat 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 | $0.00085 | $0.01521 |
| Opus 5 | $0.00043 | $0.00760 |
| Sonnet 5 | $0.00017 | $0.00304 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
mainframe-testing-strategy 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing strategy
Build enough evidence to catch a meaningful regression without testing the same guarantee repeatedly. Tests protect observable behavior; they are not a test count, coverage percentage, or architectural ceremony.
Apply this strategy within the role assigned by the calling agent. An
implementation owner may create, change, and run tests while delivering the
behavior. An audit-only recipient evaluates existing evidence and records
confirmed gaps through mainframe-ticket; it does not implement the behavior
or author, rewrite, weaken, or suppress tests.
Start from the guarantee
Before choosing a test, name the behavior that must remain true and the failure the test should catch. If neither can be stated, do not manufacture a test.
- For a bug, reproduce the reported failure at the smallest surface where it is observable.
- For business rules, validation, calculations, permissions, lifecycle changes, and state transitions, prepare the failing test before implementation when the behavior can be expressed automatically.
- For a refactor with intentionally unchanged behavior, use existing tests or a focused characterization test to hold the affected contract stable.
- For exploratory work, discover the intended guarantee first, then establish the test before treating the result as complete.
- For documentation-only, generated, or mechanically verifiable changes, use the relevant deterministic check instead of inventing an application test.
Red evidence is useful only when it proves the missing or broken behavior. A test that fails because of unrelated setup is not red evidence.
Choose the cheapest faithful observation
Test at the lowest-cost surface that can fail for the real defect:
| Level | Use when | Avoid when |
|---|---|---|
| Unit | A pure rule, calculation, parser, validator, state transition, or other defined contract can be observed without I/O | The defect is in wiring or boundary semantics |
| In-process integration | Several owned components must cooperate, but real external infrastructure adds no relevant behavior | Mocks would replace the contract being tested |
| Real-boundary integration | PostgreSQL queries, migrations, indexes, transactions, locking, filesystem formats, queues, or external contracts are the risk | It merely repeats business logic already proven cheaply |
| End-to-end | The complete user journey, deployment wiring, or browser behavior is the contract | It enumerates business-rule variations that a lower level can prove faster |
| Characterization | Legacy behavior must be held stable before a safe change | It permanently substitutes for expressing intended behavior |
What ships with it
1 file 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.
- 2d ago First seen · 139 lines · 85 tokens per session scan A 7fdfdbc89a91
mainframe-testing-strategy is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 12d ago), licensed MIT. It adds 85 tokens to every session and 1,521 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 2026-08-31.
Other skills, from other repositories
discord-webhook
Send trading alerts, signals, and analysis summaries to Discord via webhook. Integrates with realtime-alert-pipeline, trading-brain, and trade-journal-analytics.
agentforge-protocol
Use when doing non-trivial coding with Hermes, OpenClaw, Claude Code, Codex CLI, or similar autonomous coding agents. Orchestrates Karpathy-style minimal-change discipline, grill-plan intake, TDD, systematic debugging, subagent-driven implementation, spikes, and pre-commit review into one end-to-end workflow.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
edge-to-edge
Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…