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 skills/iamcxa/kc-claude-plugins/e2e-testnpx skills add iamcxa/kc-claude-plugins --skill e2e-testgit clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsWrote 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/iamcxa/kc-claude-plugins/e2e-test)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/e2e-test"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/e2e-test.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 | $0.00053 | $0.14928 |
| Opus 5 | $0.00026 | $0.07464 |
| Sonnet 5 | $0.00011 | $0.02986 |
| Haiku 4.5 | $0.00005 | $0.01493 |
Grade B, and why
e2e-test scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
COMPILER=$(find ~/.claude/plugins -name "e2e-compile.js" -path "*/e2e-pipeline/bin/*" -print -quit 2>/dev/null) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Verify external** — pause browser automation and verify external service side-effects. The LLM uses available tools (MCP, curl, API calls, DB queries) to fulfill each check. See test-runner § 2m. How it starts
The opening of the file, as written. The whole thing — 1,214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Test Orchestrator
Resolve browser E2E test flows and dispatch the e2e-test-runner agent for execution.
Invocation
/e2e-test [flow-name|--tag tag|--all] [--mapping name] [--site alias] [--all-sites] [--suite name] [--pr NUMBER] [--issue ISSUE-ID] [--video] [--no-compile] [--no-teams] [--model MODEL]
| Arg | Effect |
|---|---|
flow-name |
Run a specific flow by filename (without .yaml) |
--tag smoke |
Run all flows tagged with smoke |
--all |
Run every flow in .claude/e2e/flows/ |
--mapping name |
Select a specific mapping file (without .yaml) |
--pr 940 |
Post summary as PR comment after execution |
--issue DRC-2779 |
Include issue context in report header |
--all-sites |
Discover all mappings and run applicable flows on each site |
--site alias |
Run only the specified site's steps from a cross-site flow (mutually exclusive with --all-sites and --suite) |
--suite name |
Run a specific suite from .claude/e2e/suites/<name>.yaml |
--video |
Enable screen recording + GIF generation (auto-enabled when --pr is used) |
--no-compile |
Skip auto-compile and compiled script run after LLM execution |
--no-teams |
Force subagent mode even when Agent Teams is available |
--model MODEL |
Override default agent model (e.g., --model sonnet). Default: haiku for test runners |
Prerequisites
- agent-browser installed globally 2. Dev server running 3. Mapping file in
.claude/e2e/mappings/4. Flow files in.claude/e2e/flows/
The owned runtime treats the first open as an infrastructure transaction.
Before any flow step, require the browser receipt to report
first_navigation.status: verified. A non-zero open or any other lifecycle
status is infrastructure failure, not an application verdict.
Optional owned local services
If the user provides a manifest or .claude/e2e/services.json exists, resolve
service_runtime to ${CLAUDE_PLUGIN_ROOT}/bin/e2e-local-service-runtime.js,
generate one service_run_id, and use <top-level report_dir>/local-services as the absolute service_state_dir. Run
preflight then start before dispatching any browser attempt. The
orchestrator alone runs stop after all browser/trace cleanup, including
error paths.
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 · 1,214 lines · 53 tokens per session scan B 9aaa6f4e40de
e2e-test is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 14,928 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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.
playwright-cli
官方Microsoft Playwright CLI网页自动化工具，支持所有主流浏览器的无头/有头自动化操作，包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。.
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.