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 PramodDutta/qaskills --skill copilot-testing-patternsgit clone --depth 1 https://github.com/PramodDutta/qaskillsWrote 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/pramoddutta/qaskills/copilot-testing-patterns)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/copilot-testing-patterns"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/copilot-testing-patterns/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/pramoddutta/qaskills/copilot-testing-patterns"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/copilot-testing-patterns.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 | $0.00048 | $0.05202 |
| Opus 5.5 | $0.00019 | $0.02081 |
| Sonnet 5.5 | $0.00010 | $0.01040 |
| Haiku 4.5 | $0.00005 | $0.00520 |
Grade C, and why
GitHub Copilot Testing Patterns scanned grade C with 1 finding 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 1mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- .github/copilot/instructions.md --> How it starts
The opening of the file, as written. The whole thing — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Testing Patterns Skill
You are an expert in leveraging GitHub Copilot for test automation. When the user asks you to generate tests with Copilot, optimize Copilot suggestions for testing, use Copilot Chat for test debugging, or configure Copilot for testing workflows, follow these detailed instructions.
Core Principles
- Context is king -- Copilot generates better tests when it has access to the source code, existing test patterns, and project conventions. Keep relevant files open and organized.
- Comment-driven generation -- Write descriptive comments before test functions to guide Copilot's suggestions. The comment becomes the specification.
- Pattern establishment -- Write 2-3 example tests manually, then let Copilot follow the pattern. It excels at pattern continuation.
- Iterative refinement -- Accept Copilot's initial suggestion, then refine. It is faster to edit a 80% correct suggestion than to write from scratch.
- Chat for complex scenarios -- Use Copilot Chat for multi-step test generation, test refactoring, and debugging failed tests.
- Workspace awareness -- Copilot uses open files as context. Keep the source file and existing test file open when generating new tests.
- Review everything -- Copilot generates plausible but potentially incorrect tests. Every suggestion must be reviewed for correctness, completeness, and style.
Project Structure
src/
services/
user-service.ts
user-service.test.ts # Keep test next to source
utils/
validators.ts
validators.test.ts
components/
Button/
Button.tsx
Button.test.tsx
.github/
copilot/
instructions.md # Custom instructions for Copilot
test-patterns.md # Test pattern examples
.vscode/
settings.json # Copilot configuration
Copilot Custom Instructions for Testing
<!-- .github/copilot/instructions.md -->
# Test Generation Instructions
When generating tests, follow these conventions:
- Use vitest with TypeScript
- Follow Arrange-Act-Assert (AAA) pattern
- Name tests: "should [expected behavior] when [condition]"
- Group tests in describe blocks by function name
- Mock external dependencies using vi.mock()
- Include edge cases: null, undefined, empty values, boundaries
- Include error cases for every function that can throw
- Use strict TypeScript types (no `any`)
- Add meaningful assertion messages
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.
- 1mo ago First seen · 539 lines · 48 tokens per session scan C 320b604dc7ac
GitHub Copilot Testing Patterns is a skill published in the GitHub repository PramodDutta/qaskills (238 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 5,202 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…
analyze-failures
Triage Katalon True Platform/TestOps test failures and file defects. Use when you need to investigate failed test results, classify each failure as product defect vs automation defect vs environment/data issue, cluster failures by common signature, find likely root cause from execution data, and optionally create…
vibeflow-hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Use when a defect was observed and the evidence is in hand — an error message, a failing log, real data misbehaving — wherever…
code-review
Reviews code for bugs, security issues, and best practices.
quality-postmortem
Analyze escaped defects and test suite health through blameless postmortems. Covers bug pattern analysis, test suite health reviews, 5 Whys root cause analysis, process improvement cycles, and postmortem/retro meeting templates with action item tracking. Use when: "QA retro," "escaped bugs," "postmortem," "quality…
bug-reproducer
Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix. Also turn bug reports, stack traces, screenshots, failing behavior, support tickets, and regressions into minimal reproducible cases with red-to-green evidence. Use when…