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/gopherguides/gopher-ai/e2e-verifynpx skills add gopherguides/gopher-ai --skill e2e-verifygit clone --depth 1 https://github.com/gopherguides/gopher-aiWrote 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/gopherguides/gopher-ai/e2e-verify)<a href="https://agentmods.dev/skills/gopherguides/gopher-ai/e2e-verify"><img src="https://agentmods.dev/badge/skills/gopherguides/gopher-ai/e2e-verify.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 | $0.00069 | $0.08806 |
| Opus 5 | $0.00034 | $0.04403 |
| Sonnet 5 | $0.00014 | $0.01761 |
| Haiku 4.5 | $0.00007 | $0.00881 |
Grade A, and why
e2e-verify 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 yesterday.
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 — 758 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Verify
Plugin Resource Resolution
<PLUGIN_ROOT> is notation. Replace it with a concrete absolute plugin root before every resource read or command:
- Codex: Start from the directory containing the absolute selected
SKILL.mdpath, then ascend two directories (skills/<name>-> plugin root). - Claude Code: Bind it to the injected
${CLAUDE_PLUGIN_ROOT}value.
Before requesting decisions or delegating work, read
<PLUGIN_ROOT>/lib/driver-interaction.md and follow its
cross-platform capability-binding rules.
Read <PLUGIN_ROOT>/lib/decision-gates.md before resolving a missing
target or other workflow choice.
Bind the invocation arguments as SKILL_ARGS for $go-workflow:e2e-verify by
reading <PLUGIN_ROOT>/lib/skill-arguments.md with this Claude Code compatibility payload:
$ARGUMENTS
source "<PLUGIN_ROOT>/lib/github-rest.sh"
Core Principle: Visual Verification is Non-Negotiable
Every screenshot you take MUST be read and visually inspected. Taking a screenshot without reading it is useless. The entire point of E2E testing is to verify what the USER sees, not just what the DOM contains.
After every mcp__chrome-devtools-mcp__take_screenshot, you MUST:
- Read the screenshot using your multimodal vision capabilities
- Compare it to the spec — read the issue/PR description and verify the screenshot matches what was requested
- Describe what you see — document the visual state in your results (layout, content, styling, errors)
- Flag discrepancies — if what you see doesn't match the spec, report it as a finding
DOM checks (console errors, network requests) supplement visual verification — they do NOT replace it. A page can have zero console errors and zero network failures but still look completely wrong.
Parse Arguments
Extract PR number and mode from SKILL_ARGS:
MODE="verify"
PR_ARG=""
for arg in $SKILL_ARGS; do
case "$arg" in
verify|fix-and-verify|investigate|ship-prep|ship|fix-and-ship) MODE="$arg" ;;
*) if echo "$arg" | grep -qE '^[0-9]+$'; then PR_ARG="$arg"; fi ;;
esac
done
echo "MODE=$MODE PR_ARG=$PR_ARG"
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +13 lines 94091e8517bb
- 5d ago First seen · 745 lines · 69 tokens per session scan A 9708d6955ba1
e2e-verify is a skill published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 8,806 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 2026-08-30.
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-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.
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.