Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/textura-agency/next16-claude-starternpx agentmods add skills/textura-agency/next16-claude-starter/payload-adminWrote 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.
[](https://agentmods.dev/skills/textura-agency/next16-claude-starter/payload-admin)<a href="https://agentmods.dev/skills/textura-agency/next16-claude-starter/payload-admin"><img src="https://agentmods.dev/badge/skills/textura-agency/next16-claude-starter/payload-admin/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.
<a href="https://agentmods.dev/skills/textura-agency/next16-claude-starter/payload-admin"><img src="https://agentmods.dev/badge/skills/textura-agency/next16-claude-starter/payload-admin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00161 | $0.01621 |
| Opus 5.5 | $0.00064 | $0.00648 |
| Sonnet 5.5 | $0.00032 | $0.00324 |
| Haiku 4.5 | $0.00016 | $0.00162 |
Grade A, and why
payload-admin 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The admin's look and its guide
An owner judges the CMS in the first minute: does it look like their site,
and can they find the hero? This skill is how the reference site's admin went
from "it hurts the eyes, everything merges" to a quiet, branded tool with its
own manual. Kits: admin and guide (bash .claude/skills/payload-cms/scaffold.sh admin guide).
Principles (each was a correction from the owner)
- Light only (
admin.theme: "light"). One theme done well beats two half-done. - Calm, not loud. The first skin was bold and "hurt the eyes"; the one that stuck: pale ground, one white panel per screen, 13px muted labels, headings that step down by size not weight, the accent only on what can be pressed.
- Nothing merges. Every tab a bordered pill, nested groups as soft panels with small headings (not a second big title on a vertical rule), array rows in one rounded clipped frame (Payload's own 4px corners otherwise show through).
- Hover = colour only. No fills, underlines or shadows; no transitions or animation added (starter motion rules). Payload's own are kept.
- The site's marks: wordmark on the login card, favicon in the nav.
- The sidebar is the site: Home page (numbered, scroll order) → Site → Pages & documents → Insights → Help → Settings last.
- The editor's words everywhere: labels by what the reader sees ("Accent (highlighted part)"), a one-line note per global with the rule that matters before Save, row labels from the row's own copy ("03 · Design & ID").
§Skin — src/app/(payload)/custom.css
- Fill the Tier 1 block at the top (
--admin-surface/ground/field/line/ navy/ink/muted/accent/accent-strong/accent-deep/good/bad/live) from the site's--raw-*values inglobals.css. Those are the only raw colours in the file; Payload's whole--color-base-*ramp and--color-success-*are mixed from them (color-mix, oklab).--admin-groundis a paler tint of the site's ground — the site's own ground is usually too strong for a full-screen form. - Fonts: add
@font-faceblocks for the site's self-hosted files (family "Site Sans") — aurl()that doesn't resolve fails the build, so the kit ships none and falls back to the system stack. - Unlayered rules beat Payload's
@layer— no!importantneeded. - Settings (users, media) is Payload's first group because collections list
before globals; the skin moves it last with flex
order. Keep that block. - Check contrast:
--admin-mutedon--admin-surface≥ 4.5:1.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 98 lines · 161 tokens per session scan A 9aa7ead9248d
payload-admin is a skill published in the GitHub repository textura-agency/next16-claude-starter (137 stars, last pushed 3d ago), licensed Unlicense. It adds 161 tokens to every session and 1,621 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.