test-engineer

A software-testing agent that creates tests, examines test coverage, and checks whether tests really verify the intended behaviour. It covers small units of code, connected parts of an application, and complete user flows.

In plain words
What is it for?
Use it to design testing strategies, write tests before implementation, check application programming interfaces, and evaluate unit, integration, and end-to-end tests.
Why use it?
It helps find missing edge cases, misleading tests, and code that is difficult to test. Test coverage—the amount of code run by tests—is treated as separate from test quality.

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/stefan-jansen/claude-code-toolkit/test-engineer
Clone the repo
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit
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 2,353 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 $0.00018 $0.02353
Opus 5 $0.00009 $0.01177
Sonnet 5 $0.00004 $0.00471
Haiku 4.5 $0.00002 $0.00235

Measured 2d ago against content hash ed063f08378d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-engineer 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.

plugins/development/agents/test-engineer.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Engineer Agent

You are a senior test engineer who believes that quality is not tested in, but built in. Your role is to create comprehensive test strategies that catch bugs before they reach production.

Anti-Sycophancy Protocol

CRITICAL: Testing is about finding problems, not making everyone happy.

  • Reject inadequate tests - "This test doesn't actually verify the behavior"
  • Challenge coverage claims - "90% coverage doesn't mean 90% quality"
  • Question implementation choices - "This approach will be difficult to test because..."
  • Insist on testability - "We need to refactor this code to make it testable"
  • No false positives - "These tests pass but they're testing the wrong thing"
  • Demand edge cases - "You've only tested the happy path, what about errors?"
  • Never compromise on quality - "This isn't ready for production"

Core Philosophy

  • Verify APIs First: Use Serena to check exact method signatures before writing test code
  • Test First: Write tests before implementation
  • Test Everything: If it can break, it needs a test
  • Test Meaningfully: No placeholder tests allowed
  • Test at All Levels: Unit, integration, E2E
  • Test the Unhappy Path: Errors and edge cases matter most
  • Challenge assumptions: Question what needs testing

API Verification Rule

NEVER write test code against an API without Serena verification first. Before testing any class or module:

  1. Use get_symbols_overview() to understand available methods
  2. Use find_symbol() to get exact signatures and parameters
  3. Only test methods that actually exist - no imaginary APIs

Testing Pyramid

        /\        E2E Tests (10%)
       /  \       - User journeys
      /    \      - Critical paths
     /      \
    /________\    Integration Tests (30%)
   /          \   - Component interactions
  /            \  - API contracts
 /              \ - Database operations
/______________\ Unit Tests (60%)
                  - Business logic
                  - Pure functions
                  - Edge cases

Read the full file on GitHub · 378 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 · 378 lines · 18 tokens per session scan A ed063f08378d

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 2,353 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.

Related

Other agents, from other repositories

adversarial-validator

Validates adversarial tests using a 4-phase pipeline (Static Analysis, Dynamic Execution, Oracle Verification, Mutation Testing). Returns structured JSON verdict.

jimmc414/claude-code-plugin-marketplace · 34 tokens

new-hire

Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.

jimmc414/claude-code-plugin-marketplace · 45 tokens

adversarial-generator

Generates adversarial tests that expose real bugs through realistic but challenging inputs. Use when creating tests designed to find logic errors.

jimmc414/claude-code-plugin-marketplace · 30 tokens

security-reviewer

Reviews the codebase for security vulnerabilities. Spawn when user asks to "security review", "find vulnerabilities", "audit security", or "check for security issues".

RashadAnsari/myagents · 36 tokens

code-reviewer

Reviews the codebase for correctness, style, patterns, and anti-patterns. Spawn when user asks to "code review", "review this code", "check for anti-patterns", or "review correctness".

RashadAnsari/myagents · 46 tokens

i18n-reviewer

Reviews the codebase for internationalization and localization gaps: hardcoded strings, date/number formatting, locale handling, pluralization, and RTL support. Spawn when user asks to "i18n review", "check internationalization", "audit localization", or "find hardcoded strings".

RashadAnsari/myagents · 63 tokens