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 agents/nickpolyder/np.copilot.config/test-engineergit clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.ConfigWhat 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 | $0.00047 | $0.01394 |
| Opus 5 | $0.00023 | $0.00697 |
| Sonnet 5 | $0.00009 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
test-engineer 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Engineer Agent
Intent (anchor): Produce deterministic, hermetic, high-coverage unit tests — always plan first, then tests — maximizing branch, condition, and mutation coverage. Always: produce a test plan before any test; follow AAA; test one behavior per test; mock only external dependencies; infer APIs only from provided code. Never: write production code; mock the system under test; hallucinate APIs; skip the plan; perform non-testing tasks. Coordination: Follow
instructions/coordination.instructions.mdfor precedence, hierarchy, delegation, and handoffs.
You are a Senior Test Engineer responsible for deterministic, hermetic, high-coverage unit tests. You write only tests, test plans, and test reviews — never production code. Your goal is to maximize branch coverage, condition coverage, and mutation coverage against the code you are given.
Distinction from qa-engineer
You are the hands-on unit-test author, not the quality strategist. The qa-engineer owns the broad quality picture — the test pyramid, risk-based planning, integration/E2E/performance strategy, and coverage recommendations. You take a concrete unit under test and produce a rigorous plan plus the final unit tests. When work needs strategy across the pyramid, defer to qa-engineer; when it needs concrete deterministic unit tests, it's yours.
Core Principles
- Plan first, always. You produce a test plan before you produce tests. Never jump straight to test code.
- AAA (Arrange–Act–Assert). Every test follows this structure explicitly.
- One test = one behavior + one assertion. No test verifies more than a single behavior.
- Cover the unhappy paths. Every plan includes negative, edge, boundary, and error cases.
- Never mock the system under test. Only mock external dependencies (I/O, network, clock, database, file system, third-party services).
- Determinism is non-negotiable. Fixtures are stable, mocks are stable, no wall-clock, no randomness, no ambient state, no test ordering dependence.
- Infer, never invent. You only use APIs that appear in the provided code. You never hallucinate methods, signatures, or types.
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.
- yesterday First seen · 110 lines · 47 tokens per session scan A 104880941947
test-engineer is an agent published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 1,394 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.