Borrowing it
Nothing to install: this file belongs to different-ai/agent-bank. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/different-ai/agent-bank/main/.opencode/skill/test-staging-branch/SKILL.mdgit clone --depth 1 https://github.com/different-ai/agent-bankWrote 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/different-ai/agent-bank/test-staging-branch)<a href="https://agentmods.dev/skills/different-ai/agent-bank/test-staging-branch"><img src="https://agentmods.dev/badge/skills/different-ai/agent-bank/test-staging-branch/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/different-ai/agent-bank/test-staging-branch"><img src="https://agentmods.dev/badge/skills/different-ai/agent-bank/test-staging-branch.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 | $0.00021 | $0.03530 |
| Opus 5 | $0.00010 | $0.01765 |
| Sonnet 5 | $0.00004 | $0.00706 |
| Haiku 4.5 | $0.00002 | $0.00353 |
Grade A, and why
test-staging-branch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I Do
End-to-end test feature branches on Vercel preview deployments:
- Wait for Vercel deployment to complete
- Login via Chrome MCP (Gmail OTP flow)
- Test the specific feature
- Report results on GitHub (without leaking sensitive data)
Prerequisites
- Chrome DevTools MCP configured
- Vercel CLI authenticated with
--scope prologe - Access to Gmail for OTP codes
- GitHub CLI (
gh) authenticated
Workflow
1. Wait for Deployment
# Get latest preview deployment for the branch
BRANCH="feat/your-branch-name"
LATEST=$(vercel ls --scope prologe 2>/dev/null | grep -i "$BRANCH" | head -1 | awk '{print $2}')
# Or get the most recent deployment
LATEST=$(vercel ls --scope prologe 2>/dev/null | head -1 | awk '{print $2}')
echo "Deployment URL: $LATEST"
# Wait for Ready status (up to 5 min)
vercel inspect "$LATEST" --scope prologe --wait --timeout 5m
Output to check:
status: ● Ready→ proceed to testingstatus: ● Building→ still buildingstatus: ● Error→ check build logs
2. Login Flow (Token-Efficient)
CRITICAL: Minimize snapshots. Each snapshot costs tokens.
// Step 1: Navigate to preview deployment
chrome_navigate_page({ url: 'https://your-deployment-url.vercel.app' });
// Step 2: Wait for page load, take ONE snapshot
chrome_wait_for({ text: 'Sign in', timeout: 10000 });
chrome_take_snapshot();
// Step 3: Click login button (find uid from snapshot)
chrome_click({ uid: 'login-button-uid' });
// Step 4: Wait for Privy modal, take snapshot
chrome_wait_for({ text: 'Email', timeout: 5000 });
chrome_take_snapshot();
// Step 5: Enter email
chrome_fill({ uid: 'email-input-uid', value: '[email protected]' });
chrome_click({ uid: 'continue-button-uid' });
3. Get OTP from Gmail
Navigate to Gmail, find OTP code:
// Open Gmail in new tab
chrome_new_page({ url: 'https://mail.google.com' });
// Wait for inbox
chrome_wait_for({ text: 'Inbox', timeout: 30000 });
// Take snapshot to find latest email
chrome_take_snapshot();
// Click on Privy email (should be recent)
chrome_click({ uid: 'privy-email-row-uid' });
// Wait for email to load
chrome_wait_for({ text: 'verification code', timeout: 5000 });
// Extract OTP with script (faster than snapshot)
chrome_evaluate_script({
function: `() => {
const body = document.body.innerText;
const match = body.match(/\\b\\d{6}\\b/);
return match ? match[0] : null;
}`,
});
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 · 528 lines · 21 tokens per session scan A 9aa8542cf4d1
test-staging-branch is a skill published in the GitHub repository different-ai/agent-bank (249 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 3,530 once invoked, about $0.0001 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
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
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.
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".
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.
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…