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/agent-hellboy/mcp-runtime/qa-e2e-uinpx skills add Agent-Hellboy/mcp-runtime --skill qa-e2e-uigit clone --depth 1 https://github.com/Agent-Hellboy/mcp-runtimeWhat 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 | $0.00133 | $0.03135 |
| Opus 5 | $0.00067 | $0.01568 |
| Sonnet 5 | $0.00027 | $0.00627 |
| Haiku 4.5 | $0.00013 | $0.00314 |
Grade C, and why
qa-e2e-ui scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf "$QA_TMP"' EXIT Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Regression evidence contract: a UI pass needs browser evidence, not only curl How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA - E2E UI (live cluster)
Overview
This skill validates that the Sentinel dashboard actually works as a user experience against the real UI + API + Traefik stack. Curl checks are useful smoke gates, but they are not a substitute for browser interaction. Use Playwright and Chrome DevTools MCP whenever available to collect:
- accessibility snapshots for actionable element names and roles
- browser console messages
- network request/response evidence for UI-triggered API calls
- screenshots for visual regressions and responsive layout failures
- keyboard interaction evidence for reachable controls
services/ui/main_test.go covers handler-level behavior. This skill covers
browser-visible workflows: role-gated navigation, session transitions, forms,
filters, tables, modals, copy controls, destructive actions, public-host
defenses, and whether rendered UI data matches backend truth.
Header / CSP / lockout / secret-leak checks live in qa-e2e-security; do not
duplicate them here unless the symptom is visible in the UI.
Regression evidence contract: a UI pass needs browser evidence, not only curl or unit tests. For changed auth, role, or API-key behavior, cover both a user-identity session and a no-user-identity or denied session so role-gating regressions surface before merge. If browser automation is unavailable, report the UI result blocked.
Step 1 - Confirm preconditions
Do not reinstall the platform or run codegen as part of UI QA. The live cluster is the source of truth.
kubectl config current-context | grep -qx kind-mcp-runtime \
|| { echo "Run qa-cluster-bringup first"; exit 1; }
curl -fsS -o /dev/null http://localhost:18080/ \
|| { echo "Traefik port-forward not running; run: kubectl port-forward -n traefik svc/traefik 18080:8000"; exit 1; }
./bin/mcp-runtime status
Use a unique scratch directory for temporary artifacts:
QA_TMP="$(mktemp -d)"
trap 'rm -rf "$QA_TMP"' EXIT
If the live cluster has unrelated user changes, work with them. Do not retire or mutate non-temporary objects unless the user explicitly approves.
What ships with it
4 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.
- 2d ago First seen · 325 lines · 133 tokens per session scan C c84fedd600b6
qa-e2e-ui is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 133 tokens to every session and 3,135 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, 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
playwright-e2e-testing
Playwright modern end-to-end testing framework with cross-browser automation, auto-wait, and built-in test runner.
webmcp-e2e
WebMCP reverse connection gateway（pairing + static/remote モード）の E2E 結合確認を実行する。Manifold 起動 → デモページ → 拡張入り Chromium → ペアリング → tools/call 検証 → タブクローズ時エラー確認までを通し、スクリーンショット証跡を残す。remote モードでは自前 JWKS + JWT で identityKey ルーティングの分離も検証する。「webmcp の E2E」「reverse gateway の動作確認」「拡張の結合テスト」で使用。.
qa-use
E2E testing and browser automation with qa-use CLI. Use when the user needs to run tests, verify features, automate browser interactions, or debug test failures.
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
e2e-deployment-skill
Use this deployment skill to verify shared skills load during Playwright startup.
launch
Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test…