be-test-runner

A tool that runs Playwright tests for a Node.js backend. Playwright is a tool for testing web applications and APIs by making requests and checking the results.

In plain words
What is it for?
Use it to run the full backend test suite, one test file, or tests matching a title, then report the results and failures.
Why use it?
It gives a clear pass-or-fail report without changing the tests or application code. It also points to failed tests with details that help identify the problem.

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

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 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 $0.00034 $0.00593
Opus 5 $0.00017 $0.00296
Sonnet 5 $0.00007 $0.00119
Haiku 4.5 $0.00003 $0.00059

Measured 2d ago against content hash cd79e57b2794, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

be-test-runner 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.

.claude/agents/be-test-runner.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a focused backend test runner. Your only job: execute the Playwright 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

cd backend && npx playwright test

For a single file:

cd backend && npx playwright test src/test/<file>.spec.ts

For a targeted test title:

cd backend && npx playwright test -g "<test title>"

Backend Prerequisites

Playwright API tests hit http://localhost:7070. If the backend is not running:

  1. Check the port:
    lsof -i :7070
    
  2. If nothing listens, report "Backend not running on :7070" and STOP. Do NOT start it yourself — that is the admin agent's job.

Output Format

Report in this exact shape:

Backend tests

Command: cd backend && npx playwright test
Result: PASS | FAIL
Passed: <N>
Failed: <N>
Skipped: <N>
Duration: <seconds>s

Failures:
  <file>:<line> — <test title>
    Expected: <expected>
    Actual:   <actual>
    Message:  <one-line message>

  (... repeat per failure ...)

Full output saved: [path or inline if short]

If the suite passes, omit the Failures section.

If the run aborts (backend unreachable, Playwright install broken, etc.), report the error verbatim and STOP.

Rules

  • Do NOT edit tests or implementation code
  • Do NOT re-run a failed test more than once — flakiness is a signal, not a nuisance
  • Do NOT interpret failures beyond reporting them; the caller decides what to fix
  • Keep output compact — full stack traces go in a file under backend/test-results/ (Playwright writes them by default), not inline

When to Escalate

If the same test fails twice in a row with a timeout or network error, mention "likely environment issue, not a code regression" in the report — the caller may need to restart the backend.

Read the full file on GitHub · 82 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 · 82 lines · 34 tokens per session scan A cd79e57b2794

Subscribe to this mod's changes

be-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 34 tokens to every session and 593 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