Borrowing it
Nothing to install: this file belongs to nwiizo/tfmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nwiizo/tfmcp/main/.claude/skills/e2e-test/SKILL.mdgit clone --depth 1 https://github.com/nwiizo/tfmcpWrote 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/skills/nwiizo/tfmcp/e2e-test)<a href="https://agentmods.dev/skills/nwiizo/tfmcp/e2e-test"><img src="https://agentmods.dev/badge/skills/nwiizo/tfmcp/e2e-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nwiizo/tfmcp/e2e-test"><img src="https://agentmods.dev/badge/skills/nwiizo/tfmcp/e2e-test.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.00507 |
| Opus 5.5 | $0.00011 | $0.00203 |
| Sonnet 5.5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
e2e-test 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 26d 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.
What it actually says
Verify tfmcp End to End
Select coverage for the requested behavior using the existing tests:
| Test target | Primary coverage |
|---|---|
e2e_mcp_test |
RMCP lifecycle, discovery, tools/resources, raw protocol, and Streamable HTTP |
local_execution |
Real stdio subprocess and local Terraform saved-plan operations |
mcp_integration |
Supporting MCP schema and integration checks; inspect conditional shortcuts |
Inspect the selected test and setup before running it. Confirm the Terraform binary is available and compatible with the CI baseline. Some tests return early when Terraform is missing or use CI shortcuts; a successful exit alone does not prove the requested behavior ran.
Before the first run, isolate test processes from the user's home and credentials.
Use tempfile or mktemp -d for fixture directories; set subprocess home,
Terraform CLI configuration, audit paths, and state paths inside them. Remove
inherited HCP/TFE credentials, TF_TOKEN_*, and Terraform CLI argument overrides
from the test process. Inspect in-process fixtures too; a temporary project alone
does not isolate home-directory access. Keep the shell's own home unchanged.
Prefer local terraform_data fixtures with no remote backend or cloud access.
Enable apply/destroy gates only for the owned disposable fixture when that
behavior is under test. Real-account verification requires a separate explicit
request. Use real RMCP clients, Terraform, and files; do not introduce mocks.
Once isolation is established, run the relevant target and optional test filter:
rtk cargo test --locked --all-features --test e2e_mcp_test
rtk cargo test --locked --all-features --test local_execution
Assert observable protocol responses, error mapping, redaction, saved-plan/state effects, and applicable operation gates. Use loopback and disposable ports for HTTP checks. Stop only processes started by the test and remove only its own fixtures; retain artifacts when requested.
Report exercised scenarios, skips, failures, and retained paths. Fix failures caused by an implementation in scope and rerun affected checks. Follow the repository's required checks for implementation work; a focused smoke test does not establish full-suite coverage.
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.
- 26d ago First seen · 50 lines · 28 tokens per session scan A ae5c1aa72125
e2e-test is a skill published in the GitHub repository nwiizo/tfmcp (372 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 507 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
aspire-integration-testing
Write integration tests using .NET Aspire's testing facilities with xUnit. Covers test fixtures, distributed application setup, endpoint discovery, and patterns for testing ASP.NET Core apps with real dependencies.
tui-test
Control, inspect, test, and record real terminal apps with the tui-test CLI or its Rust, Python, and JavaScript APIs. Use for shells, TUI apps, text and style locators, keyboard or mouse input, terminal state, clipboard waits, screenshots, recordings, snapshots, and live terminal sessions.
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
flutter-mcp-e2e-harness
Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the fluttermcpharness package (packages/harness) — build/launch the app, attach to its VM service, drive widgets (snapshot/tap/enter text) and assert without MCP; also covers the repo showcase launcher (make…