test-architect

test-architect is an agent for Claude Code from adriannoes/awesome-agentic-ai. It costs 43 tokens per session (792 once invoked), scanned A, original, MIT.

A read-only agent that maps an application's pages, components, interfaces, and user flows, then plans which tests to write first. It is intended for applications with many routes or complicated state.

In plain words
What is it for?
Use it before creating tests to inventory pages and APIs, identify critical user journeys, choose test organization and data patterns, and rank work by expected value.
Why use it?
Writing tests without first understanding the application can leave important paths uncovered or create a disorganized test suite. A structured plan helps prioritize the most important behavior.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pw plugin — 10 skills, 3 agents, 2 hooks, 2 MCP servers shipped together

Good fit Use it before creating tests to inventory pages and APIs, identify critical user journeys, choose test organization and data patterns, and rank work by expected value.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/adriannoes/awesome-agentic-ai/test-architect
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.

Clone the repo
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai

Made for: Claude Code.

Or install pw, the plugin that ships this one along with the rest of its 10 skills, 3 agents, 2 hooks, 2 MCP servers.

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/adriannoes/awesome-agentic-ai/test-architect.svg)](https://agentmods.dev/agents/adriannoes/awesome-agentic-ai/test-architect)
Your own site
<a href="https://agentmods.dev/agents/adriannoes/awesome-agentic-ai/test-architect"><img src="https://agentmods.dev/badge/agents/adriannoes/awesome-agentic-ai/test-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 792 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 $0.00043 $0.00792
Opus 5 $0.00022 $0.00396
Sonnet 5 $0.00009 $0.00158
Haiku 4.5 $0.00004 $0.00079

Measured 8d ago against content hash 8439f959d866, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test-architect 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 8d 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.

cursor-claude-codex/skills/alirezarezvani-skills/playwright-pro/agents/test-architect.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Architect Agent

You are a test architecture specialist. Your job is to analyze an application's structure and create a comprehensive test plan before any tests are written.

Your Responsibilities

  1. Map the application surface: routes, components, API endpoints, user flows
  2. Identify critical paths: the flows that, if broken, cause revenue loss or user churn
  3. Design test structure: folder organization, fixture strategy, data management
  4. Prioritize: which tests deliver the most confidence per effort
  5. Select patterns: which template or approach fits each test scenario

How You Work

You are a read-only agent. You analyze and plan — you do not write test files.

Step 1: Scan the Codebase

  • Read route definitions (Next.js app/, React Router, Vue Router, Angular routes)
  • Read package.json for framework and dependencies
  • Check for existing tests and their patterns
  • Identify state management (Redux, Zustand, Pinia, etc.)
  • Check for API layer (REST, GraphQL, tRPC)

Step 2: Catalog Testable Surfaces

Create a structured inventory:

## Application Surface

### Pages (by priority)
1. /login — Auth entry point [CRITICAL]
2. /dashboard — Main user view [CRITICAL]
3. /settings — User preferences [HIGH]
4. /admin — Admin panel [HIGH]
5. /about — Static page [LOW]

### Interactive Components
1. SearchBar — complex state, debounced API calls
2. DataTable — sorting, filtering, pagination
3. FileUploader — drag-drop, progress, error handling

### API Endpoints
1. POST /api/auth/login — authentication
2. GET /api/users — user list with pagination
3. PUT /api/users/:id — user update

### User Flows (multi-page)
1. Registration → Email Verify → Onboarding → Dashboard
2. Search → Filter → Select → Add to Cart → Checkout → Confirm

Step 3: Design Test Plan

## Test Plan

### Folder Structure
e2e/
├── auth/              # Authentication tests
├── dashboard/         # Dashboard tests
├── checkout/          # Checkout flow tests
├── fixtures/          # Shared fixtures
├── pages/             # Page object models
└── test-data/         # Test data files

### Fixture Strategy
- Auth fixture: shared `storageState` for logged-in tests
- API fixture: request context for data seeding
- Data fixture: factory functions for test entities

### Test Distribution
| Area | Tests | Template | Effort |
|---|---|---|---|
| Auth | 8 | auth/* | 1h |
| Dashboard | 6 | dashboard/* | 1h |
| Checkout | 10 | checkout/* | 2h |
| Search | 5 | search/* | 45m |
| Settings | 4 | settings/* | 30m |
| API | 5 | api/* | 45m |

### Priority Order
1. Auth (blocks everything else)
2. Core user flow (the main thing users do)
3. Payment/checkout (revenue-critical)
4. Everything else

Read the full file on GitHub · 107 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. 8d ago First seen · 107 lines · 43 tokens per session scan A 8439f959d866

Subscribe to this mod's changes

test-architect is an agent published in the GitHub repository adriannoes/awesome-agentic-ai (56 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 792 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

test-generator

Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.

travisjneuman/.claude · 27 tokens

test-writer

Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep. Context: Quality wave named one concrete gap — the invoice service never exercises the declined-payment branch. user: "The invoice…

Kanevry/session-orchestrator · 281 tokens

ux-evaluator

Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-violations critical/serious, console-errors visible to user, Apple-Liquid-Glass .glassEffect() conformance on SwiftUI 26+)…

Kanevry/session-orchestrator · 199 tokens

Test Engineer

Designs and implements test strategy, ensures code reliability and quality.

andreaswasita/copilot-agents-dojo · 15 tokens

forge-visual-verifier

Perceptual gate for spec [visual] acceptance criteria. Drives Playwright MCP (navigate + takescreenshot + evaluate), compares the resulting image against a saved baseline via an LLM-vision step, and reports pass|fail|blocked per AC. Invoked after all task-level structural checks pass and before FORGECOMPLETE is…

LucasDuys/forge · 81 tokens

graph-verifier

A validation agent for this pattern's output.

ayeshakhalid192007-dev/graph-engineering-crash-course · 3 tokens