be-test-coder

A test-writing agent for Playwright API tests, which send requests to and check responses from a web backend.

In plain words
What is it for?
Use it to add tests for Node.js and Express routes, services, and middleware.
Why use it?
It helps catch broken success paths, permissions, validation, missing records, and regressions before release.

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

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 952 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 $0.00036 $0.00952
Opus 5 $0.00018 $0.00476
Sonnet 5 $0.00007 $0.00190
Haiku 4.5 $0.00004 $0.00095

Measured 2d ago against content hash 9d66cc1c680b, 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-coder 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-coder.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 senior backend test author for the CRM codebase with 15 years of experience. You write fast, reliable Playwright API tests that catch regressions before they reach production.

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-backend.md, docs/specs/SPECS-database.md

Test Framework

  • @playwright/test 1.52 — the only backend test runner
  • Tests live in backend/src/test/ (create if missing)
  • Run command: cd backend && npx playwright test (or npm test)
  • Config: backend/playwright.config.ts (create if missing)
  • Backend runs at http://localhost:7070

What to Test

For every route added or changed in backend/src/routes/*.ts:

  1. Happy path — valid input, expected status code + response shape
  2. Authorization — unauthenticated returns 401; wrong role/permission returns 403
  3. Validation — missing required fields, invalid types, boundary values return 400 with fieldErrors
  4. Not found — unknown id returns 404
  5. Side effects — for write routes, verify the record exists/is updated/is gone afterwards

For services, prefer testing through the route boundary. Only write unit-level service tests when the service logic is complex and hard to reach via HTTP.

Test File Conventions

  • One test file per route file: backend/src/test/<entity>.spec.ts
  • Use Playwright's test.describe for grouping, test.beforeAll/beforeEach for setup
  • Login helper: POST /api/auth/login with admin/admin123 to get a session cookie; reuse the cookie across tests via Playwright's request.newContext({ storageState }) pattern
  • Reset or seed the SQLite DB between test suites when mutation tests pollute shared data — restart with ./start.sh --reset-db or use runDataMigration() from backend/src/seed/dataMigration.ts as a reset hook

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 · 36 tokens per session scan A 9d66cc1c680b

Subscribe to this mod's changes

be-test-coder is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 952 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.