deploy-watch

deploy-watch is a command for coding agents from eddiebelaval/squire. It costs 0 tokens per session (569 once invoked), scanned A, original, MIT.

A command that checks the status of a Vercel website deployment, where Vercel is a service that builds and hosts web projects. It can report whether a deployment is still building, live, failed, queued, or canceled.

In plain words
What is it for?
Use it to inspect the latest deployment, wait for it to become live, report failures, and perform a health check after a successful deployment.
Why use it?
It saves you from repeatedly checking deployment dashboards and can monitor progress at regular intervals.

Command

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.

agentmods
npx agentmods add commands/eddiebelaval/squire/deploy-watch
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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.

agentmods badge for deploy-watch

README.md
[![agentmods](https://agentmods.dev/badge/commands/eddiebelaval/squire/deploy-watch.svg)](https://agentmods.dev/commands/eddiebelaval/squire/deploy-watch)
Your own site
<a href="https://agentmods.dev/commands/eddiebelaval/squire/deploy-watch"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/deploy-watch.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00569
Opus 5 $0.00000 $0.00284
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured 4d ago against content hash f2d18ca488d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-watch 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 4d 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.

1. `curl -s -o /dev/null -w "%{http_code}" https://{production-url}` to verify HTTP 200
commands/deploy-watch.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deploy-watch - Monitor Vercel Deployment Status

Watch a Vercel deployment until it's live, errored, or timed out. Designed to be used with /loop for hands-free monitoring.

Pre-computed Context

PROJECT_NAME=$(basename $(pwd))
HAS_VERCEL=$(test -f .vercel/project.json && echo "yes" || echo "no")
CURRENT_BRANCH=$(git branch --show-current)

Project: $PROJECT_NAME Branch: $CURRENT_BRANCH

Usage

/deploy-watch                    # Check latest deployment status (one-shot)
/loop 30s /deploy-watch          # Poll every 30s until live

Arguments

$ARGUMENTS

Workflow

Step 1: Get Latest Deployment

Run: vercel ls --limit 3 2>/dev/null

Parse the output to identify:

  • Deployment URL
  • State (BUILDING / READY / ERROR / QUEUED / CANCELED)
  • Age (how long ago it started)

Step 2: Report Status

Output a single concise line based on state:

  • QUEUED/BUILDING: [BUILDING] project-abc123.vercel.app — started Xs ago
  • READY: [LIVE] project-abc123.vercel.app — deployed in Xs
  • ERROR: [FAILED] project-abc123.vercel.app — check vercel logs
  • CANCELED: [CANCELED] deployment was canceled

Step 3: Health Check (READY only)

When deployment is READY:

  1. curl -s -o /dev/null -w "%{http_code}" https://{production-url} to verify HTTP 200
  2. If 200: report [LIVE] {url} — verified healthy
  3. If not 200: report [LIVE BUT UNHEALTHY] {url} — HTTP {code}

Step 4: Terminal Condition

If state is READY, ERROR, or CANCELED — this is a terminal state. Say so clearly so /loop users know they can stop:

Deploy complete. You can stop watching: Ctrl+C or /loop stop

Error Handling

  • If vercel CLI not found: report and suggest npm i -g vercel
  • If no deployments found: report "no active deployments"
  • If .vercel/project.json missing: warn but try anyway (might be auto-linked)

Notes

  • Keep output SHORT. This runs every 30s in a loop — no walls of text.
  • One status line + one action line max.
  • Do NOT re-read files or explore the codebase. Just run vercel + curl.

Read the full file on GitHub · 73 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.

  1. 4d ago First seen · 73 lines · 0 tokens per session scan A f2d18ca488d3

Subscribe to this mod's changes

deploy-watch is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 569 tokens. 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 2026-08-30.