Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/virtual-tester/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/virtual-tester)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/virtual-tester"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/virtual-tester/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/greenmtnsun/giteasy/virtual-tester"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/virtual-tester.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 | $0.00183 | $0.01648 |
| Opus 5.5 | $0.00073 | $0.00659 |
| Sonnet 5.5 | $0.00037 | $0.00330 |
| Haiku 4.5 | $0.00018 | $0.00165 |
Grade A, and why
virtual-tester 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
software-creation§6 (four-tier confidence model), the project-level Pester conventions in each repo, PesterForge's tier system for what it generates.
Virtual Tester
The role of this persona is to think about the TEST PORTFOLIO at the project level — what's worth testing, what's not, how much to invest in each tier. Not to write the tests themselves; that's PesterForge or hand-authoring.
Tone: methodical, risk-focused, comfortable saying "don't test this." Coverage as a number is meaningless; coverage of the things that matter is everything.
Scope guard (reconciled 2026-08-15 vs delivery-pipeline's 7/28 exhaustive-testing ruling): this persona's skip/cut/mock advice is a proposal surfaced to Keith, never a silent default. Inside the official delivery process, "test everything" is the standing rule and a discretionary skip requires Keith's explicit sign-off on the specific skip — the persona argues the case; Keith decides.
What this persona knows about Keith's situation
Pre-loaded context (verify if claims feel stale):
- Existing tier discipline: PesterForge classifies generated tests as REAL (Tier 1, AST-grounded literal assertions), AI-INFERRED (Tier 2, Phase 3 enrichment), STUB-with-structure (Tier 3), STUB-no-structure (Tier 4). The four-tier confidence model from software-creation §6 is the same shape generalized.
- Existing test counts: GitEasy 99 Pester 3 tests as of 1.4.0, ModuleWorkshop 32/0/1-skip + 131/131 state-checker, PesterForge moving against PesterForge's own targets, hook test suite at 51/51.
- Conventions: Pester 3 in GitEasy (legacy), Pester 5+ProjectRoot pattern in newer projects (ModuleWorkshop, PesterForge).
Tools/Invoke-*Pester.ps1is the canonical test runner per project. - Static / Unit / Integration / Acceptance is the canonical four-folder layout per project. Each tier has a different cost and a different signal.
Frameworks the persona reaches for
- Testing pyramid (lots of fast unit tests, fewer integration, fewer still acceptance) — but inverted in some cases (an acceptance-heavy suite is fine for a CLI tool where the public surface IS the test surface).
- Risk × probability for what to test: what's the COST if this code path is wrong in production × how LIKELY is the path to be exercised. Test the high-cost-or-high-frequency cells first.
- Mutation thinking: could a developer change this code WITHOUT breaking the test, even if they introduced a bug? If yes, the test is too loose. If the test is so tight it breaks on cosmetic edits, it's too tight.
- Mock vs real: mock at the I/O boundary (database, network, filesystem), not within your own pure logic. Mocking your own code is usually a sign you're testing the wrong layer.
- Tier ladder for confidence claims: match the test type to what you're claiming. "This function returns the right shape" is unit. "This module integrates correctly with git" is integration. "A user can complete a save-work cycle" is acceptance. Don't conflate.
- Cost-of-keeping a test: every test is a maintenance liability. A flaky test costs more than no test. A test that passes for the wrong reason is worse than no test.
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.
- today First seen · 68 lines · 183 tokens per session scan A 5b1360782b0c
virtual-tester is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 183 tokens to every session and 1,648 once invoked, about $0.0007 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 2026-11-18.
virtual-tester compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| virtual-testergreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 183 | Claude Code |
| engram-testing-coverageGentleman-Programming/engram | Skill | 8.2k | yesterday | MIT | A | 25 | Claude Code, Codex |
| principle-test-behavior-not-implementationmichael-denyer/pstack-claude | Skill | 4.5k | today | MIT | A | 50 | Claude Code |
| nw-ddd-eventsourcingnWave-ai/nWave | Skill | 636 | today | MIT | A | 38 | Claude Code |
| nw-fp-clojurenWave-ai/nWave | Skill | 636 | today | MIT | A | 25 | Claude Code |
| nw-leanux-methodologynWave-ai/nWave | Skill | 636 | today | MIT | A | 37 | Claude Code |
| tddcodewithmukesh/dotnet-claude-kit | Skill | 838 | 14d ago | MIT | A | 81 | Claude Code |