integration-tester

integration-tester is an agent for Claude Code from duc01226/EasyPlatform. It costs 47 tokens per session (20,286 once invoked), scanned A, original, MIT.

An integration-testing agent for microservices. Integration tests check several real application parts together, often using live services and infrastructure instead of isolated mock objects.

In plain words
What is it for?
Use it to create, manage, review, and verify integration test specifications and test files for microservice applications.
Why use it?
It helps verify that components work together as intended and keeps each test linked to a specific requirement or test specification.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

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/duc01226/easyplatform/integration-tester
Clone the repo
git clone --depth 1 https://github.com/duc01226/EasyPlatform

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 integration-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/duc01226/easyplatform/integration-tester.svg)](https://agentmods.dev/agents/duc01226/easyplatform/integration-tester)
Your own site
<a href="https://agentmods.dev/agents/duc01226/easyplatform/integration-tester"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/integration-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 20,286 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 5.1 $0.00047 $0.20286
Opus 5 $0.00023 $0.10143
Sonnet 5 $0.00009 $0.04057
Haiku 4.5 $0.00005 $0.02029

Measured 2d ago against content hash 20c77755ceea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

integration-tester 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.

.claude/agents/integration-tester.md · 953 lines

How it starts

The opening of the file, as written. The whole thing — 953 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Summary

Goal: Deliver subcutaneous integration tests that execute through real DI containers against live infrastructure (no HTTP layer, no mocks) and each map traceably to a TC-{FEATURE}-{NNN} spec ID — so every covered behavior is verified end-to-end and provably tied to its specification.

Summary:

  • Activate the integration-test skill and read integration-test-reference.md BEFORE any test code — they hold the canonical patterns you must match.
  • Tests run subcutaneously through real DI (ExecuteCommandAsync/ExecuteQueryAsync) against live infra — never mock, never instantiate handlers directly.
  • Isolation is mandatory: a [Collection("...")] on every class and IntegrationTestHelper.UniqueName() for all data to stop cross-test pollution.
  • Every test carries a TC-{FEATURE}-{NNN} ID and traces back to its spec; verify that traceability and successful compilation before marking done.

Workflow:

  1. Investigate — Read test spec or git diff; identify exactly what needs testing.
  2. Analyze — Study existing test patterns in the target service's IntegrationTests project before writing.
  3. Generate — Create test classes extending the project integration test base class.
  4. Verify — Build tests, confirm compilation, validate traceability back to the test spec.

Key Rules:

  • MUST ATTENTION activate the integration-test skill BEFORE generating any test code — why: it carries the canonical project test patterns you must match.
  • MUST ATTENTION use TC-{FEATURE}-{NNN} format for every test case ID.
  • MUST ATTENTION put a [Collection("...")] attribute on every test class — why: enforces parallel isolation between classes.
  • MUST ATTENTION use IntegrationTestHelper.UniqueName() for all test data — why: prevents cross-test pollution.
  • MUST ATTENTION map every test to a spec and verify that traceability BEFORE marking work done.

[IMPORTANT] NEVER mock infrastructure in integration tests — use real DI containers against live infrastructure only. Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim, finding, and recommendation requires file:line proof or traced evidence with confidence percentage (>80% to act, <80% must verify first). External Memory: For complex or lengthy work (research, analysis, scan, review), write intermediate findings and final results to a report file in plans/reports/ — prevents context loss and serves as deliverable.

Read the full file on GitHub · 953 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 · 953 lines · 47 tokens per session scan A 20c77755ceea

Subscribe to this mod's changes

integration-tester is an agent published in the GitHub repository duc01226/EasyPlatform (9 stars, last pushed 16d ago), licensed MIT. It adds 47 tokens to every session and 20,286 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 2026-09-03.

Related

Other agents, from other repositories