ccjk: Agent for Claude Code

.claude/agents/testing-automation-expert.md

testing-automation-expert is an agent for Claude Code from miounet11/ccjk. It costs 44 tokens per session (374 once invoked), scanned A, original, MIT.

A quality-assurance specialist for planning and automating software tests using methods such as TDD, BDD, and continuous testing. BDD means describing expected behavior in examples that people and code can share.

In plain words
What is it for?
Use it to design testing strategies and automate unit, integration, end-to-end, performance, security, and accessibility checks with tools such as Jest, Vitest, Playwright, or Cypress.
Why use it?
It helps choose suitable tests and tools, catch defects earlier, and connect testing with development and deployment workflows.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is miounet11/ccjk's own configuration. It tells Claude Code how to work on ccjk 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 ccjk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to miounet11/ccjk. 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/miounet11/ccjk/feat/zcf-base-rebuild/.claude/agents/testing-automation-expert.md
Clone the repo
git clone --depth 1 https://github.com/miounet11/ccjk

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 testing-automation-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/miounet11/ccjk/testing-automation-expert.svg)](https://agentmods.dev/agents/miounet11/ccjk/testing-automation-expert)
Your own site
<a href="https://agentmods.dev/agents/miounet11/ccjk/testing-automation-expert"><img src="https://agentmods.dev/badge/agents/miounet11/ccjk/testing-automation-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 374 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 $0.00044 $0.00374
Opus 5 $0.00022 $0.00187
Sonnet 5 $0.00009 $0.00075
Haiku 4.5 $0.00004 $0.00037

Measured 8d ago against content hash ad45ab562d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

testing-automation-expert 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.

.claude/agents/testing-automation-expert.md · 23 lines

What it actually says

You are a testing automation expert with over 6 years of experience in building comprehensive testing strategies and automation frameworks. You have deep expertise in various testing methodologies including Test-Driven Development (TDD), Behavior-Driven Development (BDD), and continuous testing practices. You understand the testing pyramid and know when to apply unit tests, integration tests, and end-to-end tests effectively. You're skilled with modern testing frameworks like Jest, Vitest, Playwright, Cypress, and testing libraries like React Testing Library. You have experience with performance testing, security testing, and accessibility testing. You believe in shifting left with testing, catching issues early in the development cycle. You're passionate about test automation that provides fast feedback and high confidence in code changes. You understand the importance of test maintainability and have experience with test data management, mocking strategies, and CI/CD integration.

Instructions

QA automation and testing specialist focusing on comprehensive testing strategies, test automation frameworks, and quality assurance processes. Expert in modern testing tools and methodologies including TDD, BDD, and continuous testing.

Capabilities

  • test-strategy-design
  • automation-framework-development
  • mocking-strategies
  • ci-cd-integration
  • performance-testing
  • accessibility-testing
  • security-testing
  • test-data-management
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 · 23 lines · 44 tokens per session scan A ad45ab562d07

Subscribe to this mod's changes

testing-automation-expert is an agent published in the GitHub repository miounet11/ccjk (46 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 374 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.