redirect-build

redirect-build is a command for Claude Code from jameywarren/shopify-claude-quickstart. It costs 14 tokens per session (330 once invoked), scanned A, original, MIT.

A command that collects old and new URL pairs and prepares a Shopify bulk redirect mutation. A redirect sends visitors and search engines from an old address to a new one.

In plain words
What is it for?
Use it to read redirect notes, compile redirect pairs, create the GraphQL mutation and variables, split large sets into batches, and check the asynchronous job status.
Why use it?
It reduces broken links after a site rebuild and requires confirmation before preparing changes, helping catch missing redirects first.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to read redirect notes, compile redirect pairs, create the GraphQL mutation and variables, split large sets into batches, and check the asynchronous job status.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jameywarren/shopify-claude-quickstart/redirect-build
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.

Clone the repo
git clone --depth 1 https://github.com/jameywarren/shopify-claude-quickstart

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 redirect-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/redirect-build/github.svg)](https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/redirect-build)
Your own site
<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/redirect-build"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/redirect-build/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.

agentmods 80×15 button for redirect-build

Your own site · 80×15
<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/redirect-build"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/redirect-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 330 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 $0.00014 $0.00330
Opus 5 $0.00007 $0.00165
Sonnet 5 $0.00003 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 9d ago against content hash 18cc7e2bb5cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

redirect-build 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 9d 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/commands/redirect-build.md · 45 lines

What it actually says

Read client-brief/navigation.md — specifically the SEO Notes section for redirects from an old site. Also scan docs/session-log.md for any redirects mentioned during the build.

Compile all redirect pairs you find, then ask:

"Here are the redirects I found: [list]. Are there any I missed? Paste them now before I build the mutation."

Wait for confirmation before building.


Then output the urlRedirectBulkCreate mutation, validated by shopify-plugin:shopify-admin:

mutation urlRedirectBulkCreate($redirects: [UrlRedirectInput!]!) {
  urlRedirectBulkCreate(redirects: $redirects) {
    job { id }
    userErrors { field message }
  }
}

With variables:

{
  "redirects": [
    { "path": "/old-path", "target": "/new-path" },
    ...
  ]
}

Conventions:

  • path is the old URL — must start with /, no domain
  • target can be a relative path or absolute URL
  • Shopify caps at 100 redirects per bulk call — split into batches if needed
  • The mutation returns a job { id } — it's async. Poll with { job(id: "...") { status } } to confirm completion

Do not execute until confirmed. Show the full mutation and variables first.

After executing, verify by querying a sample of the old URLs to confirm they resolve correctly.

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. 9d ago First seen · 45 lines · 14 tokens per session scan A 18cc7e2bb5cc

Subscribe to this mod's changes

redirect-build is a command published in the GitHub repository jameywarren/shopify-claude-quickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 330 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 2026-08-31.