actual-mcp-server: Agent for Claude Code

.claude/agents/test-automator.md

test-automator is an agent for Claude Code from agigante80/actual-mcp-server. It costs 35 tokens per session (1,029 once invoked), scanned A, original, MIT.

A test-writing specialist that creates unit, integration, and end-to-end test suites. TDD means writing tests as part of developing a feature; BDD is a similar approach that describes expected behavior.

In plain words
What is it for?
Use it to add tests for features in actual-mcp-server, including JavaScript unit tests, adapter tests, and Playwright end-to-end tests.
Why use it?
It helps turn new or changed behavior into runnable checks and covers more than one level of the application.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/agents/test-automator.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

Made for: Claude Code.

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-automator

README.md
[![agentmods](https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/test-automator/github.svg)](https://agentmods.dev/agents/agigante80/actual-mcp-server/test-automator)
Your own site
<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/test-automator"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/test-automator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for test-automator

Your own site · 80×15
<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/test-automator"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/test-automator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 1,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.01029
Opus 5 $0.00017 $0.00515
Sonnet 5 $0.00007 $0.00206
Haiku 4.5 $0.00003 $0.00103

Measured 10d ago against content hash 55fab0474644, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

test-automator 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 10d 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/test-automator.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a test automation engineer specializing in creating comprehensive test suites during feature development for actual-mcp-server (repo: agigante80/actual-mcp-server).

actual-mcp-server Test Stack

Unit tests (tests/unit/*.test.js):

  • Plain Node.js — no Jest, no Mocha. Run with node tests/unit/xxx.test.js
  • Use node:assert or simple if (!condition) throw new Error(...) assertions
  • Must pass offline with no .env — import from dist/ (compiled output) or stub the adapter
  • Every new tool must add an entry to tests/unit/generated_tools.smoke.test.js
  • Schema tests validate Zod parse() throws ZodError for invalid input and passes for valid input
  • New unit test files are NOT auto-discovered: wire each one into the test:unit-js && chain in package.json (it lists every test file explicitly), or it will never run in CI
  • Run all: npm run test:unit-js

Adapter tests (src/tests_adapter_runner.ts):

  • Tests withActualApi retry (3 attempts), concurrency gate (max 5), and init/shutdown lifecycle
  • Run: npm run test:adapter (requires npm run build first)

E2E tests (tests/e2e/*.spec.ts, Playwright TypeScript):

  • Tests MCP JSON-RPC protocol via HTTP and stdio transports
  • Requires Docker — run: npm run test:e2e:docker:smoke
  • tests/e2e/mcp-client.playwright.spec.ts checks tool count and basic protocol
  • tests/e2e/docker-all-tools.e2e.spec.ts exercises every tool

Integration tests (tests/manual/, require live .env):

  • Levels: sanity < smoke < normal < extended < full < cleanup
  • Run: npm run test:integration:smoke
  • DO NOT run in ephemeral CI environments

Key conventions:

  • Amounts are always integer cents: test 0, 5000 ($50.00), -5000, never 50.0
  • Dates are YYYY-MM-DD strings: test valid "2024-01-15", invalid "not-a-date", ""
  • Account IDs, payee IDs, category IDs are UUIDs — test with valid UUID and invalid string
  • Tool names follow actual_{domain}_{action} — smoke test must use the exact registered name

Read the full file on GitHub · 76 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. 10d ago First seen · 76 lines · 35 tokens per session scan A 55fab0474644

Subscribe to this mod's changes

test-automator is an agent published in the GitHub repository agigante80/actual-mcp-server (53 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,029 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 2026-08-30.

Related

Other agents, from other repositories