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 commands/kuadrant/mcp-gateway/e2e-testsgit clone --depth 1 https://github.com/Kuadrant/mcp-gatewayWrote 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/commands/kuadrant/mcp-gateway/e2e-tests)<a href="https://agentmods.dev/commands/kuadrant/mcp-gateway/e2e-tests"><img src="https://agentmods.dev/badge/commands/kuadrant/mcp-gateway/e2e-tests.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 5.1 | $0.00000 | $0.00656 |
| Opus 5 | $0.00000 | $0.00328 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
e2e-tests 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the test cases file as context: $ARGUMENTS
If no file path was provided above, default to: tests/e2e/test_cases.md
Context
- MCP Protocol spec: https://modelcontextprotocol.io/specification/2025-11-25
- Test MCP servers under tests/servers provide tools that can be called during e2e tests
- Helper code goes in tests/e2e/commons.go
Workflow
- Read test_cases.md and compare against existing tests in tests/e2e/happy_path_test.go
- Identify missing test cases - skip cases already covered
- Look for cases that can be extended without creating entirely new test cases
- Check for untagged cases - warn if a test case lacks a tag like [Happy]
- Add new tests following patterns below
- Run with FIt() to verify the new test passes
- Remove FIt() before completing - change back to
It()so all tests run in CI
Test Organization
[Happy]tagged cases → tests/e2e/happy_path_test.go- Other tags (e.g.,
[Error],[Edge]) → create new file named after the tag (e.g., error_test.go) - Prefix test descriptions with the tag:
It("[Happy] should do something", func() { ... })
Test Patterns
Resource cleanup (required)
var testResources = []client.Object{}
// In test:
registration := NewMCPServerResourcesWithDefaults("test-name", k8sClient)
testResources = append(testResources, registration.GetObjects()...)
registeredServer := registration.Register(ctx)
// AfterEach handles cleanup via testResources slice
Waiting for conditions
Eventually(func(g Gomega) {
g.Expect(VerifyMCPServerRegistrationReady(ctx, k8sClient, name, namespace)).To(BeNil())
}, TestTimeoutLong, TestRetryInterval).To(Succeed())
Do NOT use
deferfor cleanup - use BeforeEach/AfterEach instead- Modify existing tests without prompting for permission
Running Tests Locally
# Run specific test with focus
cd tests/e2e && go test -v -tags=e2e -run TestE2E -ginkgo.focus="test description" -timeout 10m
# Or use ginkgo CLI
ginkgo run -v --tags=e2e --focus="test description" tests/e2e/
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.
- 5d ago First seen · 70 lines · 0 tokens per session scan A e6937d0ab20f
e2e-tests is a command published in the GitHub repository Kuadrant/mcp-gateway (98 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 656 tokens. 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 commands, from other repositories
playwright
Write or update Playwright E2E tests following project conventions.
e2e
使用 Playwright 对 Web UI 进行端到端测试(支持视频录制、Trace 录制、控制台/网络日志捕获).
paul:verify
Guide manual user acceptance testing of recently built features.
plan-spec
仅在人工明确安排 UI 自动化时,根据任务、产品规则或原型生成独立行为 Spec.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.