A project command for setting up Payload CMS, a system for managing website content, with Supabase, a hosted PostgreSQL database and file-storage service. It first proposes content collections based on the pages and sample data already in the app.

Use it to add an admin area, define collections for the site's real content, save documents with uploaded images, display those images from Supabase Storage, and publish the content on a public route.

It helps avoid installing a content system against the wrong framework or database setup and checks the full path from editing content to showing it publicly. It also requires confirmation of the proposed content structure before changing configuration.

cms — Command for Claude Code by textura-agency

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/textura-agency/next16-claude-starter

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/cms/github.svg)](https://agentmods.dev/commands/textura-agency/next16-claude-starter/cms)

Your own site

<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/cms"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/cms/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/cms"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/cms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 290 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.

Model	Per session	Once invoked
Fable 5.1	$0.00012	$0.00290
Opus 5	$0.00006	$0.00145
Sonnet 5	$0.00002	$0.00058
Haiku 4.5	$0.00001	$0.00029

Measured 10d ago against content hash c84ee955fdea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cms 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 10d 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/cms.md · 26 lines

What it actually says

Set up Payload CMS for this project. Collections requested: $ARGUMENTS

Use the payload-cms skill and follow it exactly. Before installing anything:

Check the Next.js version against @payloadcms/next's peer range (>=16.2.6 <17 as of 3.88). The starter satisfies this today — verify rather than assume, and bump Next with eslint-config-next together if it does not.
Confirm a Supabase project exists with both connection strings (transaction pooler for runtime, direct for migrations). If not, run the supabase-db skill first.
Propose the collection schema from what the site actually renders — read src/views/** and src/data/mocks/** and name real content types. Confirm with the user before writing config.

Prove the loop before reporting done: /admin loads, a document with an uploaded image saves, that image renders from Supabase Storage in the browser, and the content appears on a public route. Then yarn build.

Finish by updating obsidian/backend/cms-payload.md, tech-stack.md, environment-variables.md and the changelog.

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.

10d ago First seen · 26 lines · 12 tokens per session scan A c84ee955fdea

Subscribe to this mod's changes

cms is a command published in the GitHub repository textura-agency/next16-claude-starter (113 stars, last pushed 2d ago), licensed Unlicense. It adds 12 tokens to every session and 290 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 2026-08-30.

Backend and APIs Databases PostgreSQL

cms

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

vanity-subdomains

cap-setup-wizard

new-entity

db-auth

sparc-supabase-admin

sparc-supabase-admin