What is coffeeshop-acceptance-tests?

A workflow for running browser-based acceptance tests against a coffee-shop web application. Acceptance tests check whether a complete user scenario works as expected, and these scenarios are run with Playwright against a live application stack.

Use it to run all or selected UI scenarios, verify that the application is reachable, diagnose failed tests, fix the cause, and run the checks again.

It gives a repeatable process for checking the application's user interface and investigating failures. It also limits sensitive configuration output and collects evidence such as logs, traces, and screenshots.

coffeeshop-acceptance-tests — Skill by thangchung

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.

Any agent

npx skills add thangchung/agent-engineering-experiment --skill coffeeshop-acceptance-tests

Clone the repo

git clone --depth 1 https://github.com/thangchung/agent-engineering-experiment

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/coffeeshop-acceptance-tests/github.svg)](https://agentmods.dev/skills/thangchung/agent-engineering-experiment/coffeeshop-acceptance-tests)

Your own site

<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/coffeeshop-acceptance-tests"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/coffeeshop-acceptance-tests/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/coffeeshop-acceptance-tests"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/coffeeshop-acceptance-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,749 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00157	$0.02749
Opus 5.5	$0.00063	$0.01100
Sonnet 5.5	$0.00031	$0.00550
Haiku 4.5	$0.00016	$0.00275

Measured 2d ago against content hash a23dede94e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coffeeshop-acceptance-tests scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **Order traces** (what the counter decided and why) | `GET http://localhost:5100/orders` and `/orders/{n}`: print `result.status` and each `trace.audit` row (`gate`, `gate-error`, `clarify`, `result`) and `trace.agUi`.

coffeeshop-jev/.agents/skills/coffeeshop-acceptance-tests/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

coffeeshop-jev acceptance tests

Executable UI spec for WebApp/: WebApp/acceptance/A1..A8_*.js, run by WebApp/acceptance/run.sh. Scenario meanings and per-provider results: jev_routing_research.md §17.10 (the single source of truth). UX of record: ui-prototypes/.

Run all commands from the repo root coffeeshop-jev/ unless said otherwise. Keep command output short: pipe through cut -c1-260, tail, or grep, and never print API keys.

0. Preconditions (check, don't assume)

Tools: aspire --version, playwright-cli --help | head -3, dotnet --list-sdks (needs 11.0.100-rc.2… or newer, global.json pins it).
Config: src/AppHost/appsettings.Development.json (gitignored, may start with a BOM: read it with encoding='utf-8-sig') has Parameters with decision-model-provider and that provider's decision-model-{provider}-url / -api-key (-model for microsoft), plus openai-base-url, openai-model, openai-api-key. Print only the names and the provider value, never the keys.
The provider is reachable: laya needs laya-serve on :8002 (GET /health), openjev a LAN host (often unreachable from a sandbox), microsoft a Foundry deployment (az cognitiveservices account deployment list -g <rg> -n <account> shows the deployment name to use), typesafe model jev-latest.
Offline gate first (fast, catches most regressions): dotnet build CoffeeShop.slnx -warnaserror then dotnet test tests/CoffeeShop.Tests. If these fail, fix them before any UI run.

1. Run

aspire stop >/dev/null 2>&1; sleep 2                                   # no stale stack
aspire run --detach --non-interactive --nologo --format Json >/dev/null 2>&1
sleep 35                                                               # catalog, counter, web
aspire describe --format Json | python3 -c "import sys,json;t=sys.stdin.read();d=json.loads(t[t.index('{'):]);print([(r['name'][:8],r.get('healthStatus')) for r in d['resources'] if r['name'].startswith(('web','counter','catalog'))])"
( cd "$TMPDIR" 2>/dev/null || cd /tmp; playwright-cli close >/dev/null 2>&1; playwright-cli open http://localhost:5200 >/dev/null 2>&1 )
WebApp/acceptance/run.sh               # A1..A8 (a few minutes: real decision model + LLM)
WebApp/acceptance/run.sh A1 A4         # or only some

Read the full file on GitHub · 96 lines

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.

2d ago First seen · 96 lines · 157 tokens per session scan A a23dede94e88

Subscribe to this mod's changes

coffeeshop-acceptance-tests is a skill published in the GitHub repository thangchung/agent-engineering-experiment (27 stars, last pushed 2d ago), licensed MIT. It adds 157 tokens to every session and 2,749 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

Browser automation E2E testing Testing ai-agents aiengineering foundry-local microsoft-agent-framework

browse

Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).

garrytan/gstack · 32 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

create-verification-skill

Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".

get-bb/bb · 57 tokens

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.

anthropics/skills · 35 tokens

browser-qa

A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.

hashgraph-online/awesome-codex-plugins · 58 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens

coffeeshop-acceptance-tests