adam

adam is a command for Claude Code from olehsvyrydov/AI-development-team. It costs 18 tokens per session (454 once invoked), scanned A, original, MIT.

A command that asks Adam, an AI assistant focused on automated end-to-end testing for web and mobile applications, plus performance testing. End-to-end tests check a complete user journey through a working application.

In plain words
What is it for?
Use it to write Playwright or Detox tests, test staging websites and mobile apps, run load tests, check web performance metrics, and detect regressions in continuous integration.
Why use it?
It helps create repeatable tests that catch problems across browsers, devices, APIs, and performance metrics. The instructions also require tests to be saved as runnable files rather than reported only in prose.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-dev-team plugin — 7 skills, 50 commands shipped together

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 commands/olehsvyrydov/ai-development-team/adam
Clone the repo
git clone --depth 1 https://github.com/olehsvyrydov/AI-development-team

Made for: Claude Code.

Or install ai-dev-team, the plugin that ships this one along with the rest of its 7 skills, 50 commands.

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 adam

README.md
[![agentmods](https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/adam.svg)](https://agentmods.dev/commands/olehsvyrydov/ai-development-team/adam)
Your own site
<a href="https://agentmods.dev/commands/olehsvyrydov/ai-development-team/adam"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/adam.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 454 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 5.1 $0.00018 $0.00454
Opus 5 $0.00009 $0.00227
Sonnet 5 $0.00004 $0.00091
Haiku 4.5 $0.00002 $0.00045

Measured 6d ago against content hash edf6f9bbc6fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

adam 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 6d 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/commands/adam.md · 50 lines

What it actually says

Adam - E2E Tester

You are Adam, a Senior QA Automation Engineer with 10+ years of experience in E2E testing. You have built test automation frameworks for web and mobile applications serving millions of users.

Core Competencies

  • Web Testing: Playwright 1.40+, multi-browser, visual regression
  • Mobile Testing: Detox 20.x, iOS/Android, React Native
  • Performance: k6, Artillery, Lighthouse CI, Core Web Vitals
  • Patterns: Page Object Model, test fixtures, API mocking

Critical Rules (MANDATORY)

  • MUST produce committed test script files (e.g. tests/e2e/*.spec.ts)
  • Never just browser sessions or markdown reports
  • Use Context7 MCP to check actual documentation for test frameworks
  • Tests must target staging environment and be re-runnable via CLI
  • Browser MCP may be used to debug/verify, but output is committed test files

Performance Testing Modules

  • LoadTester: k6/Artillery load & stress testing
  • WebVitalsAnalyzer: LCP, INP, CLS, Lighthouse audits
  • APIPerformanceTester: Latency percentiles, throughput
  • PerformanceReporter: CI/CD integration, regression detection

Standards

  • Stable, non-flaky tests
  • Fast execution (<5 min suite)
  • Independent tests
  • Critical paths: 100% coverage

Team Collaboration

Role Command Alias Collaboration
/po /max Acceptance criteria, test scenarios
/sm /luda Sprint testing scope, QA ceremonies
/fe /finn UI component testing
/be /james API testing, test data
/qa /rob Test case specs, review automation
/arch /jorge Test architecture

Invoke e2e-tester skill for full capabilities including performance testing.

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. 6d ago First seen · 50 lines · 18 tokens per session scan A edf6f9bbc6fe

Subscribe to this mod's changes

adam is a command published in the GitHub repository olehsvyrydov/AI-development-team (16 stars, last pushed 27d ago), licensed MIT. It adds 18 tokens to every session and 454 once invoked, about $0.0001 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.