deployment

deployment is a skill for Claude Code from MartinOlivero/saas-builder. It costs 132 tokens per session (1,477 once invoked), scanned A, original, MIT.

A workflow for putting an application into production, the environment where real users access it. It covers automated builds and releases, preview environments, monitoring errors, separating environments, and rolling back failed changes.

In plain words
What is it for?
Use it to deploy an app, set up continuous integration and delivery, create preview versions, add error tracking, separate staging from production, or prepare rollback procedures.
Why use it?
It helps turn code into a repeatable release process and makes changes easier to review and recover. It also explains which deployment work a hosting service such as Vercel already handles.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the saas-builder plugin — 18 skills, 1 hook shipped together

Good fit Use it to deploy an app, set up continuous integration and delivery…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/martinolivero/saas-builder/deployment
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 MartinOlivero/saas-builder --skill deployment
Clone the repo
git clone --depth 1 https://github.com/MartinOlivero/saas-builder

Made for: Claude Code.

Or install saas-builder, the plugin that ships this one along with the rest of its 18 skills, 1 hook.

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 deployment

README.md
[![agentmods](https://agentmods.dev/badge/skills/martinolivero/saas-builder/deployment.svg)](https://agentmods.dev/skills/martinolivero/saas-builder/deployment)
Your own site
<a href="https://agentmods.dev/skills/martinolivero/saas-builder/deployment"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-builder/deployment.svg" alt="Measured on agentmods" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,477 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.01477
Opus 5 $0.00066 $0.00739
Sonnet 5 $0.00026 $0.00295
Haiku 4.5 $0.00013 $0.00148

Measured 6d ago against content hash ca7ecfa6c048, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deployment 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 6d 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.

skills/deployment/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deployment

This skill ships your app without over-building DevOps. The key insight: Vercel already does ~80% of CI/CD and rollback for free. The skill teaches what's free, then adds the thin layer Vercel doesn't give you.

Analogy: Vercel is a modern car with airbags, ABS, and a backup camera built in. You don't bolt on your own brakes — you learn the controls, then add the one thing it lacks (a dashcam, i.e. error monitoring).

Discovery (max 3 questions, only if unknown)

  1. Is the repo already connected to Vercel (or another host)?
  2. Do you have automated tests / typecheck to gate merges on?
  3. Do you need a separate staging environment, or are preview deploys enough?

Step 1 — Deploys & previews (mostly free)

  • Connect the repo to Vercel once via the dashboard. After that: every push to a non-main branch gets an automatic Preview URL; every merge to main auto-deploys Production. No vercel deploy in CI needed for the happy path.
  • The preview URL is your review environment — reviewers test the real deployed build on each PR, not a local guess.
  • Only script a CI-driven deploy (vercel pullvercel buildvercel deploy --prebuilt) if you must deploy after CI in one pipeline, or for a non-connected repo. For a solo dev, native Git integration is less to maintain.
  • Backend / full-stack on InsForge: if the backend lives on InsForge (see the data-modeling skill), the agent deploys edge functions, runs migrations, and can deploy the frontend through the insforge-cli skill — one place, agent-operated. Vercel still fits the frontend if you prefer the most-proven host; choose by the same agentic-native vs mature-ecosystem rule. The CI gate, Sentry, env hygiene, and rollback steps below apply either way — they're host-independent.

Step 2 — Add a CI quality gate (the missing piece)

Create .github/workflows/ci.yml that runs on pull_request:

on: pull_request
jobs:
  ci:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with: { node-version: 20, cache: npm }
      - run: npm ci
      - run: npm run lint
      - run: npx tsc --noEmit
      - run: npm test
      - run: npm run build

Read the full file on GitHub · 78 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. 6d ago First seen · 78 lines · 0 tokens per session scan A ca7ecfa6c048

Subscribe to this mod's changes

deployment is a skill published in the GitHub repository MartinOlivero/saas-builder (2 stars, last pushed 18d ago), licensed MIT. It adds 132 tokens to every session and 1,477 once invoked, about $0.0007 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 2026-08-31.