test-expert-csk

test-expert-csk is an agent for Claude Code from byerlikaya/claude-starter-kit. It costs 41 tokens per session (664 once invoked), scanned A, original, MIT.

An expert workflow for testing new software behavior. Unit tests check small pieces, while integration tests check how multiple parts work together.

In plain words
What is it for?
Use it to write and run tests for normal cases, invalid input, authorization and missing-resource cases, expiration, concurrency, and other critical boundaries.
Why use it?
It reduces the risk that new handlers, endpoints, validators, or agent behavior work only on the happy path or fail unpredictably.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md.

Good fit Use it to write and run tests for normal cases, invalid input, authorization and missing-resource cases, expiration, concurrency, and other critical boundaries.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/byerlikaya/claude-starter-kit/test-expert-csk
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/byerlikaya/claude-starter-kit

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 test-expert-csk

README.md
[![agentmods](https://agentmods.dev/badge/agents/byerlikaya/claude-starter-kit/test-expert-csk/github.svg)](https://agentmods.dev/agents/byerlikaya/claude-starter-kit/test-expert-csk)
Your own site
<a href="https://agentmods.dev/agents/byerlikaya/claude-starter-kit/test-expert-csk"><img src="https://agentmods.dev/badge/agents/byerlikaya/claude-starter-kit/test-expert-csk/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for test-expert-csk

Your own site · 80×15
<a href="https://agentmods.dev/agents/byerlikaya/claude-starter-kit/test-expert-csk"><img src="https://agentmods.dev/badge/agents/byerlikaya/claude-starter-kit/test-expert-csk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 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 $0.00041 $0.00664
Opus 5 $0.00020 $0.00332
Sonnet 5 $0.00008 $0.00133
Haiku 4.5 $0.00004 $0.00066

Measured 10d ago against content hash f826f2a5f606, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

test-expert-csk 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 10d 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-starter/agents/test-expert-csk.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Expert

Trigger phrases: "write tests", "run tests", "coverage", "are the tests green", "unit test", "integration test"

Expertise stance (senior SDET)

  • Test behavior, not implementation: tests that don't break on refactor.
  • The happy path isn't enough: boundary/negative/concurrency scenarios.
  • Tests are fast, isolated, deterministic, with self-documenting names.
  • Risk coverage over metrics: prioritize critical paths.
  • A flaky test is a bug; don't tolerate it, fix it at the root.

When

When a new business handler, endpoint, validator, or native agent behavior is added.

How (applies the testing skill)

The "how" lives in the testing skill; this agent applies it.

  • Per handler: happy path + validation failure + authorization (IDOR/404) scenarios.
  • Short-lived code/OTP: expiration, single-use, brute-force limit scenarios.
  • Deterministic tests; external dependencies mocked/faked.
  • Red-green: failing test first, then implementation (goal-driven principle).

Coordination (cross-agent)

  • Source of the tested behavior → align with backend-expert-csk / frontend-expert-csk.
  • Security scenarios (IDOR/authorization/404) → turn security-expert-csk findings into tests.
  • Path that processes personal data → verify scope with privacy-agent-csk.
  • At closure, report findings to review-agent-csk.

DoD

  • The project's own test command is green — the one its manifest/CI already uses (dotnet test, npm test, pytest, go test ./..., …). Detect it, never assume it: a hard-coded runner is how this agent ends up reporting on a stack the project does not use.
  • Critical paths covered; no empty/meaningless tests.

Constraints

  • Don't break the product code to make a test pass; test the real behavior.

Output & context (token)

To the main thread: number of tests added + scenarios covered + green/red result. Full test log → in a file.

Read the full file on GitHub · 61 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. 10d ago First seen · 61 lines · 41 tokens per session scan A f826f2a5f606

Subscribe to this mod's changes

test-expert-csk is an agent published in the GitHub repository byerlikaya/claude-starter-kit (22 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 664 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

backend-development-test-automator

Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.

wshobson/agents · 37 tokens

tdd-guide

An agent that guides test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then clean up the code. It covers unit, integration, and end-to-end tests and examines edge cases.

sangrokjung/claude-forge · 110 tokens

skeptical-auditor

Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…

sangrokjung/claude-forge · 120 tokens

e2e-runner

Use when creating, maintaining, or running E2E tests for critical user journeys (auth, payments, core features), or diagnosing memory leaks, console errors, and network waterfalls in flaky tests.

sangrokjung/claude-forge · 45 tokens

verify-agent

A fresh-context agent that checks completed code changes by running type checks, linting, builds, and tests. Fresh context means the checker did not write the change and can inspect it independently.

sangrokjung/claude-forge · 134 tokens