e2e-test-engineer

e2e-test-engineer is a skill for Claude Code, Codex from lfyxhappy/lfcode. It costs 62 tokens per session (399 once invoked), scanned A, original, MIT.

A workflow for testing a complete user journey through the interface or public service, rather than checking only isolated pieces of code. End-to-end testing follows the same major path a user would take.

In plain words
What is it for?
Use it to create, improve, review, or repair tests for important workflows. It helps drive the interface, check visible results and side effects, capture useful failure evidence, and clean up test data.
Why use it?
A feature can pass unit checks while the real interface, service, permissions, or data flow is broken. This workflow tests the deployed or packaged application with controlled data and a meaningful outcome.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/lfyxhappy/lfcode/e2e-test-engineer
Any agent
npx skills add lfyxhappy/lfcode --skill e2e-test-engineer
Clone the repo
git clone --depth 1 https://github.com/lfyxhappy/lfcode

Made for: Claude Code, Codex.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/lfyxhappy/lfcode/e2e-test-engineer.svg)](https://agentmods.dev/skills/lfyxhappy/lfcode/e2e-test-engineer)
Your own site
<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/e2e-test-engineer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/e2e-test-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 399 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 $0.00062 $0.00399
Opus 5 $0.00031 $0.00199
Sonnet 5 $0.00012 $0.00080
Haiku 4.5 $0.00006 $0.00040

Measured today against content hash bca57e17c0be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

e2e-test-engineer 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 today.

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.

packages/lfcode/src/skill/lfcode/.bundle/e2e-test-engineer/SKILL.md · 29 lines

What it actually says

End-to-End Test Engineer

Verify a user-visible workflow through the deployed or packaged surface that users actually run.

Workflow

  1. Read repository instructions, the user journey, acceptance criteria, existing E2E harness, and the actual artifact or service that must be exercised.
  2. Define the smallest high-risk workflow: entry state, user actions, observable success, recoverable failure, permissions, data ownership, and cleanup.
  3. Use the repository-approved test environment and automation route. For desktop applications, follow project instructions for packaged or installed-copy validation instead of treating a source-only dev server as release evidence.
  4. Seed or create isolated data through supported setup paths, then drive the UI or public interface as a user would.
  5. Assert durable outcomes, visible feedback, navigation, and critical side effects. Prefer semantic locators and explicit readiness signals over layout coordinates and sleeps.
  6. Capture screenshots, diagnostics, logs, or artifacts only when they help explain a failure. Clean up owned data and rerun the focused workflow before broader release checks.

Boundaries

  • Keep workflow analysis and test planning read-only unless the user asks to implement or change E2E tests.
  • Do not run destructive flows against production, shared accounts, or user-owned data without explicit authorization.
  • Do not replace a product shell, bypass permissions, or rely on source-mode success when the request requires installed-artifact behavior.
  • Do not turn a transient timing issue into a permanent arbitrary wait.

Completion Check

Report the user workflow, artifact and environment exercised, setup and cleanup, assertions, diagnostics captured, verification result, and residual platform or external-service risk.

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. today First seen · 29 lines · 62 tokens per session scan A bca57e17c0be

Subscribe to this mod's changes

e2e-test-engineer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 399 once invoked, about $0.0003 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 2026-09-05.