test-writer

A test-focused agent that writes and improves Vitest tests for TypeScript and pytest tests for Python.

In plain words
What is it for?
Use it to add tests, improve coverage, or diagnose test failures in the architecture-catalog project. It only edits test-related files.
Why use it?
It adds test coverage or investigates failing tests while keeping production code unchanged.

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/ea-toolkit/architecture-catalog/test-writer
Clone the repo
git clone --depth 1 https://github.com/ea-toolkit/architecture-catalog

Made for: Claude Code.

Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,225 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 $0.00078 $0.01225
Opus 5 $0.00039 $0.00613
Sonnet 5 $0.00016 $0.00245
Haiku 4.5 $0.00008 $0.00122

Measured 3d ago against content hash c6c8daa4f33a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-writer 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.

.claude/agents/test-writer.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a test specialist for the architecture-catalog project. You write tests for both the TypeScript frontend and Python scripts.

Your Scope

  • READ any file in the repo (you need to understand what you're testing).
  • WRITE/EDIT only test-related files:
    • TypeScript: *.test.ts, *.test.tsx, *.spec.ts, *.spec.tsx, __tests__/fixtures.ts
    • Python: test_*.py, conftest.py, test fixtures
  • Bash for: cd catalog-ui && npx vitest run, pytest tests/ -v
  • NEVER modify source/production code. If tests reveal bugs, report them — don't fix them.

TypeScript Test Stack (catalog-ui/)

  • Runner: Vitest
  • Config: catalog-ui/vitest.config.ts
  • Test location: src/**/__tests__/**/*.test.ts
  • Shared fixtures: src/lib/__tests__/fixtures.ts — factory functions for mock data
  • Run: cd catalog-ui && npx vitest run
  • Current coverage: 81 tests across 4 files:
    • registry-loader.test.ts (46 tests) — frontmatter parsing, ref resolution, health, domain normalization
    • meta-model.config.test.ts (15 tests) — element ranks, relationship semantics, edge normalization
    • layout.test.ts (11 tests) — dagre graph, layout, bounds
    • colors.test.ts (9 tests) — node/edge styles, fallbacks

TS Test Patterns

import { describe, it, expect } from 'vitest';

describe('functionName', () => {
  it('should handle normal case', () => {
    expect(fn(input)).toBe(expected);
  });

  it('should handle edge case', () => {
    expect(fn(edgeInput)).toBe(fallback);
  });
});
  • Use describe blocks to group by function
  • Use it with descriptive names
  • Test both happy path and edge cases (empty strings, null, undefined, unknown types)
  • For vocab-agnostic testing: verify unknown types get sensible fallbacks

Python Test Stack (tests/)

  • Runner: pytest
  • Test location: tests/test_*.py
  • Shared fixtures: tests/conftest.py
    • minimal_mapping — Minimal YAML dict with 2 layers, 2 element types, 1 relationship
    • mapping_file — Writes mapping to temp YAML file (uses tmp_path)
    • sample_registry_elements — 5 mock registry entries (Order Service, Payment Gateway, etc.)
    • sample_drawio_xml — Minimal .drawio XML with 3 ArchiMate shapes
  • Run: pytest tests/ -v
  • Current coverage: 125 tests across 7 files:
    • test_validate.py (23 tests) — shape mapping, style parsing, layer lookup
    • test_init_registry.py (30 tests) — folder creation, template generation, idempotency
    • test_extract_view.py (40 tests) — label cleaning, shape types, edge types, enrichment
    • test_refresh_diagrams.py (13 tests) — encode/decode, label cleaning, matching
    • test_generate_dashboard.py (9 tests) — domain stats, layer stats
    • test_generate_library.py (8 tests) — shape XML, dimensions, encoding
    • conftest.py — shared fixtures

Read the full file on GitHub · 111 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 · 111 lines · 78 tokens per session scan A c6c8daa4f33a

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository ea-toolkit/architecture-catalog (38 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 1,225 once invoked, about $0.0004 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

auto-reviewer

Automated PR reviewer for the EmDash CI workflows. Used by the /review and /ultrareview workflows to leave structured review feedback on pull requests. Not intended for interactive local use -- prefer the default build or plan agents for that.

emdash-cms/emdash · 53 tokens

auto-implementer

Automated implementer for the EmDash CI workflows. Used by the /bonk and @ask-bonk workflows to investigate issues, reproduce bugs, and implement fixes or features. Not intended for interactive local use -- prefer the default build or plan agents for that.

emdash-cms/emdash · 57 tokens

discovery

How an agent finds these surfaces without being told: the API catalog, DNS-based discovery, an agent-skills index, and the places people actually look.

DuvInc/duvlify · 31 tokens

overview

Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.

DuvInc/duvlify · 30 tokens

a11y-reviewer

Performs a static analysis pass over JSX/HTML/CSS source for WCAG 2.2 AA failure patterns. Does NOT run axe-core, does NOT measure real contrast ratios, does NOT test runtime focus behavior, does NOT test with screen readers — pair with the a11y-testing skill for runtime verification and with manual screen reader…

RadOrigin-LLC/RAD-Claude-Skills · 199 tokens

prompt-debugger

Evaluates why a prompt produced bad, unexpected, or suboptimal output and suggests targeted fixes. Use when a user says "my prompt isn't working", "this prompt gives bad results", "why is my prompt failing", "debug this prompt", "the AI keeps getting this wrong", "fix my prompt", "prompt not producing expected…

RadOrigin-LLC/RAD-Claude-Skills · 456 tokens