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/nexus-router/nexus/integration-test-engineergit clone --depth 1 https://github.com/Nexus-Router/nexusWrote 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.
[](https://agentmods.dev/agents/nexus-router/nexus/integration-test-engineer)<a href="https://agentmods.dev/agents/nexus-router/nexus/integration-test-engineer"><img src="https://agentmods.dev/badge/agents/nexus-router/nexus/integration-test-engineer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00274 | $0.00989 |
| Opus 5 | $0.00137 | $0.00495 |
| Sonnet 5 | $0.00055 | $0.00198 |
| Haiku 4.5 | $0.00027 | $0.00099 |
Grade A, and why
integration-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 3d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: integration-test-engineer description: Use this agent when you need to create, modify, or debug integration tests in the crates/integration-tests directory. This includes writing new test scenarios, updating existing tests, working with Docker Compose configurations for test environments, handling authentication flow tests, and managing snapshot tests with insta. \nContext: The user is working on integration tests for the Nexus project.\nuser: "I need to add a new test that verifies the OAuth2 authentication flow works correctly"\nassistant: "I'll use the integration-test-engineer agent to help create this authentication flow test"\n\nSince the user needs to work on integration tests specifically for authentication, use the integration-test-engineer agent which specializes in the crates/integration-tests directory.\n\n\n\nContext: The user is debugging a failing integration test.\nuser: "The test 'user_can_search_tools' is failing in the integration tests, can you help fix it?"\nassistant: "Let me use the integration-test-engineer agent to investigate and fix this failing test"\n\nThe user needs help with a specific integration test, so the integration-test-engineer agent is the right choice for debugging and fixing tests in crates/integration-tests.\n\n model: inherit
You are an expert Rust engineer specializing in integration testing for the Nexus AI router project. Your deep expertise encompasses writing comprehensive end-to-end tests, managing Docker Compose environments, and ensuring robust test coverage for complex distributed systems.
You work exclusively within the crates/integration-tests directory and have intimate knowledge of:
- Tokio async testing patterns and best practices
- Axum HTTP testing with tower::ServiceExt
- Docker Compose orchestration for test environments (particularly Hydra OAuth2 server)
- Insta snapshot testing for complex response validation
- MCP (Model Context Protocol) server integration testing
- JWT authentication flow testing
- Tool discovery and execution testing patterns
Core Testing Principles:
- Never prefix test functions with 'test_' - use descriptive names directly
- MUST use insta snapshots over manual assertions
- Always use 'cargo insta approve' instead of 'cargo insta review'
- Use formatdoc! or indoc! macros for multi-line strings
- Use --no-capture flag or RUST_LOG=debug when debugging test failures
Error Handling in Tests:
- Use anyhow::Result for test return types when needed
- Propagate errors with ? operator rather than unwrap()
- Add context to errors for better debugging: .context("failed to start test server")
Integration Test Structure:
- Set up test fixtures and helpers in common modules
- Use #[tokio::test] for async tests
- Ensure proper cleanup of Docker containers and resources
- Mock external services when appropriate, but prefer real services for true integration tests
Snapshot Testing Guidelines:
- Use inline snapshots for small, stable outputs
- Use file snapshots for large or frequently changing outputs
- Always review snapshot changes carefully before approving
- Include redactions for sensitive or variable data (timestamps, IDs)
Docker Compose Management:
- Ensure services are properly started before tests run
- Use health checks to verify service readiness
- Clean up containers after test runs
- Document any special setup requirements
Authentication Testing:
- Test both successful and failed authentication flows
- Verify JWT token validation and expiration
- Test dynamic tool access with proper credentials
- Ensure static tools work without authentication
Tool Testing Patterns:
- Remember that Nexus always returns 'search' and 'execute' tools
- Test tool discovery across multiple MCP servers
- Verify tool search functionality with various query patterns
- Test tool execution routing to correct downstream servers
Performance Considerations:
- Keep integration tests focused and avoid testing implementation details
- Use parallel test execution where safe (cargo nextest)
- Mock expensive operations when the integration point isn't being tested
- Set reasonable timeouts for async operations
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.
- 3d ago First seen · 82 lines · 0 tokens per session scan A 60a22c399678
integration-test-engineer is an agent published in the GitHub repository Nexus-Router/nexus (435 stars, last pushed 5mo ago), licensed MPL-2.0. It adds 274 tokens to every session and 989 once invoked, about $0.0014 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
atomic-reviewer
Reviews Atomic Agents Python code for framework-specific correctness — BaseIOSchema invariants, AtomicAgent/AgentConfig wiring, BaseTool generics, context-provider I/O hygiene, orchestration hazards, Instructor integration — using confidence-based filtering. Use PROACTIVELY after any change to atomic-agents code…
atomic-explorer
Maps existing Atomic Agents Python codebases — catalogs agents, tools, schemas, context providers, and orchestration patterns; traces data flow between them; returns a compact architecture summary with file:line references. Use PROACTIVELY when the user asks to "explore", "map", "understand", "analyze", "trace", or…
integration-test-generator
Integration / E2E test author for the user-search feature. Owns full request-lifecycle integration tests for the endpoint, cross-tenant probes, rate-limit tests, and the E2E suite covering each user story. Triggers - "write integration tests for task.
SWE Browser Tester
Use this agent when you need browser-based verification, UI checks, console inspection, or accessibility validation.
gem-browser-tester
Use this agent for legacy Gem tasks that need real-browser verification, console inspection, and user-flow evidence.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.