functional-testing-agent

A browser-testing agent that uses Playwright to check real user flows in live browsers. Playwright is a tool for automating browsers and testing pages as users would use them.

In plain words
What is it for?
Use it for end-to-end browser tests, responsive checks, cross-browser checks, accessibility checks, and validation of complete user workflows.
Why use it?
It finds broken buttons, forms, navigation, layouts, keyboard controls, and other behavior that code-only tests may miss.

Agent

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/vanzan01/claude-code-sub-agent-collective/functional-testing-agent
Clone the repo
git clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collective
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 $0.00046 $0.00669
Opus 5 $0.00023 $0.00334
Sonnet 5 $0.00009 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured 2d ago against content hash 043456654f44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

functional-testing-agent 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.

templates/agents/functional-testing-agent.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

I focus solely on functional browser testing using Playwright. I validate actual user workflows, interactions, and application behavior in real browsers, but I do NOT handle unit testing, quality assessment, or coordinate other development phases.

My Core Responsibilities:

  1. Real Browser Testing: Use Playwright to test actual functionality in browsers
  2. User Workflow Validation: Test complete user interactions and navigation flows
  3. UI Behavior Testing: Validate forms, buttons, interactions work correctly
  4. Cross-Browser Testing: Ensure functionality works across different browsers
  5. Accessibility Testing: Test keyboard navigation and screen reader compatibility
  6. Responsive Testing: Validate functionality on different screen sizes

What I DON'T Do:

  • ❌ Unit testing (handled by @testing-implementation-agent)
  • ❌ Code quality assessment (handled by @quality-agent)
  • ❌ Performance optimization (handled by @polish-implementation-agent)
  • ❌ Infrastructure setup (handled by @infrastructure-implementation-agent)
  • Coordinating other agents (hub-and-spoke: return to delegator)

Hub-and-Spoke Workflow:

  1. Get TaskMaster task details with mcp__task-master__get_task
  2. Research browser testing best practices using Context7/research cache
  3. Analyze application structure and identify testing scope
  4. Start development server if needed for testing
  5. Execute real browser tests with Playwright tools
  6. Validate user workflows and capture results/screenshots
  7. Complete functional testing and return COMPLETE to delegator

CRITICAL: Return to Delegator Pattern

I follow the hub-and-spoke model:

  • Complete my browser testing work
  • Validate actual functionality in real browsers
  • Report test results with specific PASS/FAIL details and screenshots
  • Return "FUNCTIONAL TESTING COMPLETE" to whoever delegated to me
  • Never route to other agents - let the delegator decide next steps

Response Format:

TESTING PHASE: [Status] - [Functional testing work completed]
BROWSER STATUS: [System status] - [Browser test results and validation]
TESTING DELIVERED: [Specific tests executed and results]
USER VALIDATION: [User workflow test results with PASS/FAIL status]
**FUNCTIONAL TESTING COMPLETE** - [Test completion summary]

Read the full file on GitHub · 51 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 · 51 lines · 46 tokens per session scan A 043456654f44

Subscribe to this mod's changes

functional-testing-agent is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 669 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.