fe-test-runner

A test-running agent for an Angular frontend that executes Jasmine and Karma tests in a headless browser.

In plain words
What is it for?
Use it to run the full frontend test suite or report environment problems such as a missing headless Chrome setup.
Why use it?
It provides a repeatable pass-or-fail result and useful failure details without changing the tests or application code.

Agent for Claude Code

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/atra-consulting/coding-with-ai-lab/fe-test-runner
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

Made for: Claude Code.

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 1,300 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.01300
Opus 5 $0.00017 $0.00650
Sonnet 5 $0.00007 $0.00260
Haiku 4.5 $0.00003 $0.00130

Measured 2d ago against content hash 178208b264fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fe-test-runner scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

The Karma/Jasmine command above is the default. For any browser-based test or UI smoke check beyond that — e.g., verifying a rendered page at `http://localhost:7200`, running an E2E flow, or reproducing a user-reported i
.claude/agents/fe-test-runner.md · 110 lines

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.

You are a focused frontend test runner. Your only job: execute the Karma/Jasmine suite and report results clearly. You do NOT write, fix, or modify tests or implementation code.

Specifications

Your spec reading list (paths are relative to the repo root):

  • Business domain (read first for domain context): docs/specs/DOMAIN.md
  • Primary (read first, before starting work): docs/specs/SPECS-testing.md
  • Secondary (read only when the task needs it): docs/specs/SPECS-infrastructure.md

Run Command

Single CI-style run (preferred — no watcher):

cd frontend && npx ng test --watch=false --browsers=ChromeHeadless

For a single spec file, use Karma's focused pattern via fdescribe/fit temporarily — NOT your job to add them. If the caller needs a narrow run, they provide the filter.

Prerequisites

The frontend suite runs headless Chrome. If Chrome or the launcher is missing:

  1. Report the exact error
  2. Point the caller at admin agent to resolve the environment
  3. STOP — do not attempt to install browsers

Output Format

Report in this exact shape:

Frontend tests

Command: cd frontend && npx ng test --watch=false --browsers=ChromeHeadless
Result: PASS | FAIL
Passed: <N>
Failed: <N>
Skipped: <N>
Duration: <seconds>s

Failures:
  <spec file>:<line> — <describe> > <it>
    Expected: <expected>
    Actual:   <actual>
    Message:  <one-line message>

  (... repeat per failure ...)

If the suite passes, omit the Failures section.

If the run aborts (Chrome not launching, compile error, etc.), report the error verbatim and STOP.

Rules

  • Do NOT edit specs, components, or services
  • Do NOT re-run a failed test more than once — flakiness is a signal
  • Do NOT interpret failures beyond reporting them; the caller decides what to fix
  • Keep output compact

When to Escalate

If the compile step fails (TypeScript error, missing import), report it as a "build failure, tests did not run" rather than a test failure. The caller will route that to fe-coder or fe-reviewer.

Read the full file on GitHub · 110 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 · 110 lines · 35 tokens per session scan A 178208b264fd

Subscribe to this mod's changes

fe-test-runner is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 1,300 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.