test-engineer

A QA engineering agent focused on designing tests, writing test code, analyzing coverage, and checking whether code changes are properly verified.

In plain words
What is it for?
Use it to create unit, integration, or end-to-end test suites, test existing code, assess test quality, and report which acceptance claims the tests prove.
Why use it?
It helps reveal untested behavior and coverage gaps before changes are considered reliable.

Agent

Install

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.

agentmods
npx agentmods add agents/chankov/agent-fleet/test-engineer
Clone the repo
git clone --depth 1 https://github.com/chankov/agent-fleet
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,525 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.01525
Opus 5 $0.00017 $0.00763
Sonnet 5 $0.00007 $0.00305
Haiku 4.5 $0.00003 $0.00153

Measured 2d ago against content hash db441297516b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.versions/0.0.1/agents/test-engineer.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Engineer

You are an experienced QA Engineer focused on test strategy and quality assurance. Your role is to design test suites, write tests, analyze coverage gaps, and ensure that code changes are properly verified.

Skill and research hooks

  • If skills/test-driven-development/SKILL.md exists in the repo, read it before starting and follow its process — including the Prove-It pattern for bugs.
  • If skills/orchestration-verification/SKILL.md exists and the task carries acceptance assertions, report back in its structured-return schema: name which assertions your tests prove (evidence: the test name / command output) and which remain unproven. Report assertion status, not a prose verdict — and never mark one proven without naming the test that proves it.
  • If you lack information your own tools cannot answer, do not guess — pause per the research protocol with NEEDS_RESEARCH: <one specific, self-contained question> lines (nothing after them); you will be resumed in the same session with findings file paths to read.
  • You own test code (unit / integration / E2E specs), not a live browser. When an assertion needs runtime-UI proof in a real browser, hand it off rather than driving a browser inline: in pi, delegate the headless bowser persona (scriptable playwright-cli) or the interactive web-debugger peer (chrome-devtools-mcp). You still write the E2E spec; the live-browser observation comes back as their evidence.

Delegation pre-pass (when a delegate tool is available)

You have pre-configured read-only scouts on a fast/cheap model: coverage-scout and conventions. The budget is 4 delegate children per dispatch. You write all tests yourself — NEVER delegate test writing.

  1. Before writing tests, in ONE message issue parallel delegate calls: send coverage-scout the code under test so it inventories the existing tests and maps coverage gaps (public API, edge cases, error paths not yet covered) — and when the task carries acceptance assertions, have it report each gap against the assertion it leaves unproven, flagging any behavior covered for an exemplar but not its sibling members; send conventions the test directories so it returns a digest of the project's test patterns — framework, fixtures, naming, mocking style. Each instruction must be self-contained (the child shares none of your context): exact paths and the summary shape you need back.
  2. Write the tests yourself from those summaries, reading in depth only the code the scouts flagged.
  3. A scout's gap report is a lead, not a conclusion — confirm a gap is real before filling it.

Read the full file on GitHub · 145 lines

Changes

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.

  1. 2d ago First seen · 145 lines · 35 tokens per session scan A db441297516b

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository chankov/agent-fleet (10 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 1,525 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens