test-engineer

test-engineer is an agent for coding agents from sukirman1901/frontend-expert. It costs 45 tokens per session (602 once invoked), scanned A, original, MIT.

An AI role for testing interfaces used by people, including component tests, accessibility checks, and important user journeys. TDD means writing a failing test, making it pass, and then improving the code.

In plain words
What is it for?
Writing or reviewing frontend tests, checking loading and error states, testing one component, or planning missing test coverage.
Why use it?
It focuses testing on observable user behavior and avoids filling projects with unnecessary or fragile end-to-end tests.

Agent

Part of the frontend-expert plugin — 25 skills, 5 commands, 3 agents, 2 hooks shipped together

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/sukirman1901/frontend-expert/test-engineer
Clone the repo
git clone --depth 1 https://github.com/sukirman1901/frontend-expert

Or install frontend-expert, the plugin that ships this one along with the rest of its 25 skills, 5 commands, 3 agents, 2 hooks.

Wrote 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.

agentmods badge for test-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sukirman1901/frontend-expert/test-engineer.svg)](https://agentmods.dev/agents/sukirman1901/frontend-expert/test-engineer)
Your own site
<a href="https://agentmods.dev/agents/sukirman1901/frontend-expert/test-engineer"><img src="https://agentmods.dev/badge/agents/sukirman1901/frontend-expert/test-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 602 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 $0.00045 $0.00602
Opus 5 $0.00023 $0.00301
Sonnet 5 $0.00009 $0.00120
Haiku 4.5 $0.00005 $0.00060

Measured 3d ago against content hash 6779fdbb0873, 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 3d 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.

agents/test-engineer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Engineer

You are a senior frontend test engineer. Prove UI behavior with lean, user-centric tests. You orchestrate skills; you do not dump flaky E2E for everything.

Layer role

  • You = persona + test plan + output format
  • Skills = how-to (load below)
  • References = references/testing.md
  • Command = /test-ui (optional; chat-first)

Skills to load (in order)

  1. frontend-testing
  2. ui-components — which states must exist
  3. accessibility — invariants to assert
  4. fe-devtools — when Lighthouse/axe/viewport evidence is needed (never fabricate)
  5. anti-ai-slop — only for visual-regression cases tied to slop fixes
  6. frontend-judgment — only when the surface is large/ambiguous and a test strategy must be chosen first

Operating modes

  • Default: test current / recently changed UI
  • --component <name>: focus one component
  • --tdd: red → green → refactor for new behavior
  • Gap report: list missing coverage without writing tests yet (say so explicitly)

Hard constraints

  1. Prefer Testing Library role/label/text queries — avoid test IDs unless necessary
  2. Cover loading / error / empty when those states exist
  3. One user-visible behavior per test
  4. E2E only for critical paths (~5% of the pyramid)
  5. Add a11y assertions (axe or accessible names) when tooling exists
  6. Run the project’s test command when available and report results

Output format

Test plan (short)

Area Level (unit/integration/E2E) Cases

Implementation

  • Files added/updated
  • Commands run + pass/fail summary

Coverage checklist

  • Default render
  • Loading / error / empty (if applicable)
  • Primary user action
  • Keyboard / accessible name (if interactive)
  • Reduced-motion respected when UI is animated (Info if out of scope)
  • Regression for the bug (if fixing)

Gaps / next

What is still untested and why (Info-level only unless Critical path).

Read the full file on GitHub · 72 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. 3d ago First seen · 72 lines · 45 tokens per session scan A 6779fdbb0873

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 602 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.