What is qa-test-staging?

A staging quality check that uses a real signed-in browser session to test Compass Calendar after deployment. It checks the expected account, core user flows, changed flows, anonymous behavior, and browser errors.

Use it after a staging deploy to exercise important calendar flows, inspect console and network failures, and report evidence or request the correct connected browser session.

It prevents a false pass from an isolated browser, temporary account, or unverified login. It also keeps credentials and OAuth sign-in outside the automated process.

How KeepSoftwareSimple/compass-calendar configures Claude Code and Cod

Reuse

Borrowing it

Nothing to install: this file belongs to KeepSoftwareSimple/compass-calendar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/KeepSoftwareSimple/compass-calendar/main/.agents/skills/qa-test-staging/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/KeepSoftwareSimple/compass-calendar

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/keepsoftwaresimple/compass-calendar/qa-test-staging/github.svg)](https://agentmods.dev/skills/keepsoftwaresimple/compass-calendar/qa-test-staging)

Your own site

<a href="https://agentmods.dev/skills/keepsoftwaresimple/compass-calendar/qa-test-staging"><img src="https://agentmods.dev/badge/skills/keepsoftwaresimple/compass-calendar/qa-test-staging/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/keepsoftwaresimple/compass-calendar/qa-test-staging"><img src="https://agentmods.dev/badge/skills/keepsoftwaresimple/compass-calendar/qa-test-staging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 981 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00052	$0.00981
Opus 5.5	$0.00021	$0.00392
Sonnet 5.5	$0.00010	$0.00196
Haiku 4.5	$0.00005	$0.00098

Measured yesterday against content hash 52f8d1f0bf9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa-test-staging 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.

.agents/skills/qa-test-staging/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When

Explicitly invoked with /qa-test-staging after a staging deploy.

Steps

Select signed-in browser → core sweep → changed flows → anonymous sweep → report.

Output

Evidence of staging confidence; console/network notes.

Pass

Expected test profile verified; core flows exercised.

Anti-patterns

Do not substitute an isolated browser when a signed-in profile is required. See anti-patterns.md.

Escalate

Wrong profile, staging down, or credentials the agent must not enter.

Test Compass staging

Test https://staging.compasscalendar.com in a user-connected browser after a deploy. Prefer Cursor's browser control in Cursor, Claude-in-Chrome in Claude, or another real-profile browser tool. Do not substitute an isolated browser when the flow depends on an existing signed-in profile.

Safety boundaries

Do not enter credentials or automate Google OAuth.
Do not guess which browser profile is correct.
Verify signed-in state from the account control before changing data.
Never fall back to a temporary account and report an authenticated pass.
Stop and ask the user to connect/sign in the staging profile when no suitable session is available.
Do not delete created artifacts without explicit approval.

Expected authenticated test account: [email protected]. Temporary account indicates the anonymous/local profile.

1. Select and verify the browser

List connected browser tabs/profiles using the available browser tooling.
Navigate a fresh tab to staging.
Inspect the account control:
- expected test email → proceed
- Temporary account → this is not the authenticated target
If multiple valid sessions exist, ask the user which to use. If none exist, stop with the exact connection/sign-in action required.
Lock the selected tab/session when the browser tool supports locking.

2. Core authenticated sweep

Confirm each action from rendered state, not merely a successful click. Capture a screenshot when supported and inspect console/network errors throughout.

Read the full file on GitHub · 124 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.

yesterday First seen · 124 lines · 52 tokens per session scan A 52f8d1f0bf9d

Subscribe to this mod's changes

qa-test-staging is a skill published in the GitHub repository KeepSoftwareSimple/compass-calendar (226 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 981 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Browser automation E2E testing React Testing TypeScript calendar google google-calendar nodejs

qa-test-staging next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
qa-test-stagingKeepSoftwareSimple/compass-calendar	Skill	226	today	MIT	A	52	Claude Code, Codex
playwright-page-objectsbartstc/vite-ts-react-template	Skill	123	15d ago	MIT	A	30	Claude Code
webapp-testingDDS-Solutions/AI-TadPole-OS	Skill	8	2d ago	MIT	A	28	Claude Code
next-cache-components-optimizervercel/next.js	Skill	143k	yesterday	MIT	A	123	Claude Code
next-partial-prefetching-optimizervercel/next.js	Skill	143k	yesterday	MIT	A	82	Claude Code
merge-seedkriasoft/react-starter-kit	Skill	24k	6d ago	MIT	A	49	Claude Code, Codex
ux-acceptance-coordinatoremdash-cms/emdash	Skill	14k	today	MIT	A	59	Claude Code, Codex

compass-calendar: Skill for Claude Code