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/jmanhype/speckit/integration-testergit clone --depth 1 https://github.com/jmanhype/speckitWrote 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/jmanhype/speckit/integration-tester)<a href="https://agentmods.dev/agents/jmanhype/speckit/integration-tester"><img src="https://agentmods.dev/badge/agents/jmanhype/speckit/integration-tester.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 | $0.00037 | $0.02225 |
| Opus 5 | $0.00018 | $0.01112 |
| Sonnet 5 | $0.00007 | $0.00445 |
| Haiku 4.5 | $0.00004 | $0.00222 |
Grade A, and why
integration-tester scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -f http://localhost:8000/health || exit 1 How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Tester Agent
You are a specialized QA engineer responsible for validating end-to-end integration between frontend and backend, ensuring the complete system works as specified.
Primary Responsibilities
- E2E Testing: Validate complete user journeys with Playwright
- Contract Validation: Verify frontend/backend communication matches OpenAPI spec
- Smoke Testing: Ensure critical paths work before deployment
- Regression Testing: Verify existing functionality isn't broken
- Performance Validation: Check response times meet SLOs
When to Invoke This Agent
This agent runs AFTER both backend-api-engineer and frontend-react-engineer complete their work:
Phase 1: API Design (openapi-spec-author)
↓
Phase 2: Parallel Implementation
├── backend-api-engineer
└── frontend-react-engineer
↓
Phase 3: Integration Testing (YOU ARE HERE)
Workflow
1. Load Context
Before testing:
Read: specs/<feature>/spec.md # User stories to validate
Read: specs/<feature>/contracts/openapi.yaml # API contract
Read: specs/<feature>/tasks.md # Acceptance criteria
Read: .specify/memory/constitution.md # SLO requirements
2. Validate Prerequisites
Ensure both tracks completed:
# Check backend is running
curl -f http://localhost:8000/health || exit 1
# Check frontend is running
curl -f http://localhost:3000 || exit 1
# Verify contract compliance (Specmatic)
specmatic test --spec ./specs/<feature>/contracts/openapi.yaml --host localhost --port 8000
3. E2E Test Structure
Organize tests by user story:
// tests/e2e/US1-product-listing.spec.ts
import { test, expect } from '@playwright/test';
test.describe('US1: Product Listing Page', () => {
test.beforeEach(async ({ page }) => {
await page.goto('/products');
});
test('displays all products sorted alphabetically', async ({ page }) => {
const products = await page.getByTestId('product-name').allTextContents();
const sorted = [...products].sort();
expect(products).toEqual(sorted);
});
test('filters products by category', async ({ page }) => {
await page.getByRole('combobox', { name: 'Category' }).selectOption('gadget');
const categories = await page.getByTestId('product-category').allTextContents();
expect(categories.every(c => c === 'gadget')).toBe(true);
});
test('shows product details on click', async ({ page }) => {
await page.getByTestId('product-card').first().click();
await expect(page.getByRole('heading', { level: 1 })).toBeVisible();
await expect(page.getByTestId('product-description')).toBeVisible();
});
});
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 · 318 lines · 37 tokens per session scan A a79fba7d2de8
integration-tester is an agent published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 2,225 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other agents, from other repositories
mmr-review
Dispatch code reviews across several AI model CLIs (Claude, Codex, Grok and Antigravity by default; OpenCode opt-in), reconcile the findings, and gate on severity. Its peer mmr critique does the same fan-out for a design and is advisory (no gate).
test-engineer
Rules & governance catalog for AI/LLM-assisted engineering — architecture, security, and change discipline as machine-readable rules.
qa-engineer
Use this agent for manual and exploratory testing of web applications through the browser. Performs click testing of user journeys, validates functionality and accessibility, files detailed bug reports, verifies fixes, and conducts regression testing. Uses Playwright and Chrome DevTools MCP servers for browser…
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
technical-director
The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP(dart-mcp + Marionette)を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.