shipit: Skill for Claude Code

.claude/skills/deployment-architecture/SKILL.md

deployment-architecture is a skill for Claude Code from nikzlabs/shipit. It costs 42 tokens per session (686 once invoked), scanned A, original, Apache-2.0.

A guide to how ShipIt deploys projects through hosting services such as Vercel, Cloudflare Pages, or Netlify. A deployment is the process of publishing a project so people can use it online.

In plain words
What is it for?
Use it when changing automatic deployment behavior, GitHub deployment status polling, or the deployment section of the pull-request lifecycle view.
Why use it?
It explains why a push can start a deployment automatically and where deployment status is collected and shown.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is nikzlabs/shipit's own configuration. It tells Claude Code how to work on shipit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shipit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nikzlabs/shipit. 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/nikzlabs/shipit/main/.claude/skills/deployment-architecture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nikzlabs/shipit

Made for: Claude Code.

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-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikzlabs/shipit/deployment-architecture.svg)](https://agentmods.dev/skills/nikzlabs/shipit/deployment-architecture)
Your own site
<a href="https://agentmods.dev/skills/nikzlabs/shipit/deployment-architecture"><img src="https://agentmods.dev/badge/skills/nikzlabs/shipit/deployment-architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 686 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00042 $0.00686
Opus 5 $0.00021 $0.00343
Sonnet 5 $0.00008 $0.00137
Haiku 4.5 $0.00004 $0.00069

Measured 6d ago against content hash c7085d4b7e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deployment-architecture 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.

.claude/skills/deployment-architecture/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deployment Architecture

ShipIt uses automatic deployments via platform Git integration — no manual deploy button or ShipIt-managed build. Users connect their repo to Vercel, Cloudflare Pages, or Netlify once, and every push triggers the platform's native deploy pipeline. Since ShipIt auto-pushes after every agent turn, deploys happen automatically.

How It Works

  1. User imports their GitHub repo on a hosting platform (Vercel, Cloudflare Pages, Netlify)
  2. ShipIt's auto-push after agent turns triggers the platform's deploy pipeline
  3. The platform creates GitHub Deployments on each deploy
  4. ShipIt's PrStatusPoller fetches deployment status via the GitHub GraphQL API
  5. Deployment status (URLs, state) appears in the PR lifecycle card

Components

Component Location Role
PrStatusPoller orchestrator/pr-status-poller.ts Polls GitHub for PR + deployment status
GitHubDeploymentStatus shared/types/deployment-types.ts Type for deployment status data
PrStatusSummary.deployments shared/types/github-types.ts Deployment data on PR status
DeploymentStatusRow client/components/PrLifecycleCard.tsx UI row showing deploy status
Settings "Deployments" tab client/components/Settings.tsx Setup guide with platform links

Deployment Status Tracking

The PrStatusPoller GraphQL query includes commit.deployments(last:5) to fetch the latest deployments for each PR's head commit. Each deployment includes:

  • environment — e.g. "Production", "Preview"
  • state — pending, success, failure, error, in_progress, etc.
  • environmentUrl — the deployed URL (preview or production)
  • creator — the platform that created the deployment (e.g. "vercel[bot]")

This data is broadcast via SSE pr_status events and displayed in the PR lifecycle card's DeploymentStatusRow component.

Setup Guide

The Settings dialog has a "Deployments" tab under the "Project" section that shows:

  • Links to import repos on Vercel, Cloudflare Pages, and Netlify
  • A brief explanation of how auto-deploy works with ShipIt

Read the full file on GitHub · 61 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 · 61 lines · 42 tokens per session scan A c7085d4b7e69

Subscribe to this mod's changes

deployment-architecture is a skill published in the GitHub repository nikzlabs/shipit (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 686 once invoked, about $0.0002 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.