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 skills add mostafa-drz/claude-skills --skill audit-ui-e2egit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/audit-ui-e2e)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/audit-ui-e2e"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/audit-ui-e2e/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.
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/audit-ui-e2e"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/audit-ui-e2e.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00152 | $0.03582 |
| Opus 5 | $0.00076 | $0.01791 |
| Sonnet 5 | $0.00030 | $0.00716 |
| Haiku 4.5 | $0.00015 | $0.00358 |
Grade A, and why
audit-ui-e2e 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit UI End-to-End
Walk a running UI with beginner's mind. Drive the browser through every interactive surface inside the target scope, log each rough edge as a structured finding, and ship a triage-board the user can hand to a teammate or paste into a ticket system.
The target can be anything reachable in a browser — a local dev server, staging, production, a specific route, a single modal, an entire flow, a deployed PR preview. Branch context is detected and used as enrichment when the URL is on localhost, but isn't required.
Preferences
On startup, use the Read tool to load ~/.claude/skills/audit-ui-e2e/preferences.md. If missing, use defaults.
Defaults:
default-depth:standardauto-open-triage:true(open the resulting viewer in Chrome at the end)destructive-default:skip(Delete / Purge / Drop / Wipe buttons skipped unless--include-destructive)localhost-port-hint:3000(used only to ask "should I start the dev server" when localhost is the target and the port is dead)
Context
On startup, use Bash to detect (best-effort, skip on failure):
- Whether the user is currently in a git repo (
git rev-parse --is-inside-work-tree) - If so: current branch, recent commits ahead of main, files changed
- A Linear/Jira ticket key from the branch name if pattern matches (e.g.
feat/ais-2060-…) - If the target URL is on
localhost: whether the port is listening
These are used to seed the audit's metadata + plan, not as preconditions. The skill works fine on any URL with no git context.
Command routing
Check $ARGUMENTS:
help→ show help, then stopconfig→ interactive setup, then stopreset→ delete preferences, confirm, then stop- bare URL or path as first arg → target (e.g.
/audit-ui-e2e https://app.example.com/dashboardor/audit-ui-e2e /w/30/meetings) --scope <description>→ free-text scope hint (e.g.--scope "the new export buttons in the header")--depth quick|standard|thorough→ override default depth--include-destructive→ don't skip destructive actions; clicks Delete/Purge/etc. but honors confirmation dialogs (missing confirms become findings)- anything else (including empty) → run the audit, ask for target
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.
- 10d ago First seen · 284 lines · 152 tokens per session scan A f1f50cec97b6
audit-ui-e2e is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 28d ago), licensed MIT. It adds 152 tokens to every session and 3,582 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
shipkit-qa-visual
Visual QA using Playwright as a browser automation library. --setup installs Playwright and creates ui-goals.json; default mode writes inline scripts to navigate, screenshot, and report against goals.
playwright-pro
Production-grade Playwright testing skill for E2E suites, flaky test diagnosis, browser automation, migration from Cypress/Selenium, CI integration, visual checks, and regression validation.
browser-qa-delivery
Validate a Design Studio HTML artifact in the sandbox browser, fix rendering and runtime defects, then deliver exactly the tested file.
ag-testar-e2e
QA Playwright automatizado: navega como usuario, captura console/rede/UI quebrada e gera relatorio para fluxos criticos e regressao.
ag-testar-e2e-batch
Suite E2E completa com pre-flight de infra, batches de 10-20 testes, auto-fix de falhas (seletores/mocks/timing), retry ate 3 ciclos, progresso em /tmp/e2e-progress.md.
ag-referencia-playwright
Patterns canonicos Playwright 2026 — Chromium isolado, web-first assertions, locators semanticos, persistent context. Carregar antes de QAT/E2E/browser test.