Shell Tool · engineering · Sentinel

Verify a Deployment

Hit the live URL, capture status code, screenshot the homepage — prove runtime works (deploy success is not).

Updated today

View as MarkdownsentinelsonnetcheapMax 5 turns

Overview

Implements verify-deploy/SKILL.md. After any deploy (CF, Vercel, Fly, anything), runs curl against the live URL to capture status code + headers, hits critical endpoints listed by the user, screenshots the homepage with ultron-screenshot. Surfaces runtime errors that wrangler/vercel-cli can't catch (broken bindings, missing env, 500 from app code). Returns a structured pass/fail report.

When to use this

right after any deploy
user says 'is it live?' / 'check the deploy' / 'verify production'
deploy succeeded but the user wants proof the app actually works

When NOT to use this

before any deploy has happened → deploy first
the deploy itself failed → debug the deploy CLI output instead

Example prompts

verify my-app.pages.dev is live and serving

check the deploy at https://foo.workers.dev — should return 200

is the production deploy actually working?

Inputs and output

Inputs

Field	Description
`url`	the live URL to probe
`endpoints`	optional list of critical paths to also hit

Output

Status codes per endpoint + screenshot path + pass/fail summary.

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`cheap`	A small, fast model. Cents per invocation.
Turn budget	`5`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`synchronous`	Runs inside the live turn; result lands in the same response.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`shell_exec`	tool

Tags: engineering, verify, audit

Execution template

Shell tools dispatch via a command template. The model substitutes user inputs into the placeholders before firing the underlying tool.

shell_execbash

1curl -I {{url}}; ultron-screenshot {{url}}; follow verify-deploy/SKILL.md

Related skills

Skill	What it does
Spin up a Web App	Scaffold a fresh web app in /work, start the dev server, surface the live preview URL.
Clone a Website	Fire ultron-capture: spider the site, deploy a branded clone, surface the URL when ready.
Build an Agent	Spin up an autonomous agent on the agent-runtime satellite — try templates first, custom build only if no fit.
Deploy to Cloudflare	Ship the current /work to Pages, Workers, or Containers — then verify the live URL.
Push to GitHub	Initialize /work as a git repo, create the GitHub repo, push, return the URL.
Swap Page Sections	Reorder <section> blocks in a minified HTML file with byte-level safety.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "verify-deployment"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/verify-deployment/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.