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.
npx agentmods add agents/stefan-jansen/claude-code-toolkit/test-engineergit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat 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.
| Model | Per session | Once 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 |
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.
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:
- Use
get_symbols_overview()to understand available methods - Use
find_symbol()to get exact signatures and parameters - 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
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.
- 2d ago First seen · 378 lines · 18 tokens per session scan A ed063f08378d
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.
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.
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.
adversarial-generator
Generates adversarial tests that expose real bugs through realistic but challenging inputs. Use when creating tests designed to find logic errors.
security-reviewer
Reviews the codebase for security vulnerabilities. Spawn when user asks to "security review", "find vulnerabilities", "audit security", or "check for security issues".
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".
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".