tfmcp: Skill for Claude Code

.claude/skills/e2e-test/SKILL.md

e2e-test is a skill for Claude Code from nwiizo/tfmcp. It costs 28 tokens per session (507 once invoked), scanned A, original, MIT.

An end-to-end testing skill for tfmcp, an MCP server that connects clients to Terraform operations. End-to-end tests exercise complete flows such as server communication, transports, and real local Terraform work.

In plain words
What is it for?
Use it to verify MCP lifecycle and HTTP or standard-input transports, tool discovery, protocol behavior, and local Terraform saved-plan operations.
Why use it?
It checks behavior across system boundaries instead of only testing individual functions. It also isolates test credentials, home directories, state, and temporary files to avoid affecting the user's environment.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is nwiizo/tfmcp's own configuration. It tells Claude Code how to work on tfmcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tfmcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/nwiizo/tfmcp/main/.claude/skills/e2e-test/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nwiizo/tfmcp

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 e2e-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/nwiizo/tfmcp/e2e-test/github.svg)](https://agentmods.dev/skills/nwiizo/tfmcp/e2e-test)
Your own site
<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.

agentmods 80×15 button for e2e-test

Your own site · 80×15
<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>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00028 $0.00507
Opus 5.5 $0.00011 $0.00203
Sonnet 5.5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 26d ago against content hash ae5c1aa72125, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.claude/skills/e2e-test/SKILL.md · 50 lines

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.

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. 26d ago First seen · 50 lines · 28 tokens per session scan A ae5c1aa72125

Subscribe to this mod's changes

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.

Related

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.

Hmbown/CodeWhale · 25 tokens

webapp-testing

Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.

Hmbown/CodeWhale · 32 tokens

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.

Aaronontheweb/dotnet-skills · 43 tokens

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.

microsoft/tui-test · 67 tokens

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.

Arenukvern/mcp_flutter · 38 tokens

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…

Arenukvern/mcp_flutter · 117 tokens