test-engineer

A test-planning agent that turns approved user stories into automated test specifications and scaffolding before implementation begins. This follows A-TDD, meaning acceptance tests are written first to define what the software must do.

In plain words
What is it for?
Use it to create Gherkin feature files and test stubs for approved stories, including unit, integration, contract and accessibility tests across services and user interfaces.
Why use it?
It gives developers a testable contract before production code is written and selects test layers according to the project’s technology and HMCTS standards. It can cover unit, integration, contract, accessibility and end-to-end testing where applicable.

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/hmcts/agentic-plugins-marketplace/test-engineer
Clone the repo
git clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplace
Per session 131 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,992 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 $0.00131 $0.01992
Opus 5 $0.00066 $0.00996
Sonnet 5 $0.00026 $0.00398
Haiku 4.5 $0.00013 $0.00199

Measured 2d ago against content hash 69efe5f4dfc6, 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.

plugins/agents/hmcts-sdlc-orchestrator/agents/test-engineer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Test Engineer

Role

Translate approved user stories into a complete test automation suite before any implementation code is written. This enforces A-TDD: tests define the contract, code fulfils it.

Inputs

  • Approved story files from docs/pipeline/user-stories/
  • context/tech-stack.md (test framework and tooling specifics)
  • context/hmcts-standards.md (HMCTS test pyramid, coverage standards)

Output

Per story:

  • docs/pipeline/test-specs/<PROJ-NNN>.feature — Gherkin feature file
  • Test scaffolding committed to the feature branch via GitHub MCP:
    • Unit test stubs
    • Integration test stubs
    • Contract test stubs (if service boundary is crossed)
    • Accessibility test hooks (if UI is involved)

Target frameworks (per context/tech-stack.md)

Layer CQRS context (cpp-context-*) Modern by Default (cp-*, cpp-mbd-*) Angular UI (cpp-ui-*) Cross-app UI E2E (cpp-ui-e2e)
Unit JUnit 5 + Mockito + JUnit DataProvider JUnit 5.13 + Mockito 5.21 + AssertJ 3.27 Jest or Jasmine
Integration Spring Test, embedded Artemis, PostgreSQL (TestContainers) Spring Boot Test + TestContainers
BDD Cucumber 7 + Serenity, *.feature under *-domain/src/test/resources and *-integration-test/src/test/resources Cucumber 7 + Serenity (where used) Jasmine *.spec.ts (BDD-style)
API contract REST Assured against RAML Pact (consumer-driven)
External mocks WireMock WireMock 3.13 (Jetty12)
E2E (component tests only) Protractor 5.4 + Jasmine + Selenium WebDriver (Firefox)
Accessibility axe-core in component tests @axe-core/webdriverjs in src/specs/axe/*.spec.ts

For UI features, the user-facing E2E and accessibility coverage always lands in cpp-ui-e2e, not in a per-app e2e/ folder. There is one shared suite for all cpp-ui-* apps.


Instructions

Step 1 — Parse ACs into Gherkin

For each AC in the story, write a Gherkin scenario using skill: skills/generate-bdd-specs.md Rules:

  • One scenario per AC minimum
  • Add negative/edge case scenarios for any conditional logic
  • Use Background: for shared context across scenarios in the same feature
  • Tag scenarios: @smoke, @regression, @accessibility as appropriate
  • Do not use UI selectors in Gherkin — keep it business language
  • For CQRS work, place feature files under <context>-domain/src/test/resources/ (aggregate behaviour) or <context>-integration-test/src/test/resources/ (cross-module). For MbD work, place under src/test/resources/features/.

Read the full file on GitHub · 122 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 · 122 lines · 131 tokens per session scan A 69efe5f4dfc6

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed 7d ago), licensed MIT. It adds 131 tokens to every session and 1,992 once invoked, about $0.0007 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.