payload: Skill for Claude Code

.agents/skills/ui4/SKILL.md

ui4 is a skill for Claude Code, Codex from payloadcms/payload. It costs 25 tokens per session (6,035 once invoked), scanned A, original, MIT.

A manually started workflow for changing the appearance of Payload UI components to match a Figma design, a shared interface-design file.

In plain words
What is it for?
Use it to reskin Payload UI components from a Figma URL, check icon imports, compare available icons, and flag icons that must be added.
Why use it?
It helps identify icon differences between the design and the existing code before changing a component.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

This is payloadcms/payload's own configuration. It tells Claude Code and Codex how to work on payload 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 payload configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is } from '../../../__helpers/e2e/helpers.js'.

About the project

Payload is an open-source, full-stack framework for Next.js that provides a TypeScript backend and an administration panel for managing application data and content. Developers use it as a headless content management system or as the backend and application framework for their own projects. The catalogue add-ons help agents work with Payload projects and their development workflows.

payloadcms/payload · 45,565 stars · on GitHub · payloadcms.com

Reuse

Borrowing it

Nothing to install: this file belongs to payloadcms/payload. 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/payloadcms/payload/main/.agents/skills/ui4/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/payloadcms/payload

Made for: Claude Code, Codex.

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 ui4

README.md
[![agentmods](https://agentmods.dev/badge/skills/payloadcms/payload/ui4/github.svg)](https://agentmods.dev/skills/payloadcms/payload/ui4)
Your own site
<a href="https://agentmods.dev/skills/payloadcms/payload/ui4"><img src="https://agentmods.dev/badge/skills/payloadcms/payload/ui4/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 ui4

Your own site · 80×15
<a href="https://agentmods.dev/skills/payloadcms/payload/ui4"><img src="https://agentmods.dev/badge/skills/payloadcms/payload/ui4.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,035 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. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 369
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Excessive Agency · line 504
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00025 $0.06035
Opus 5.5 $0.00010 $0.02414
Sonnet 5.5 $0.00005 $0.01207
Haiku 4.5 $0.00003 $0.00604

Measured 1mo ago against content hash 0eb129800c6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui4 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 1mo 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.

.agents/skills/ui4/SKILL.md · 646 lines

How it starts

The opening of the file, as written. The whole thing — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Payload UI Reskin (ui4)

Figma URL is REQUIRED. If not provided, ask before proceeding.


Process

Step 0: Icon Scan

Goal: Identify icon dependencies before starting work.

  1. Scan component files for icon imports:

    grep -E "from.*icons|import.*Icon" packages/ui/src/elements/ComponentName/
    
  2. List existing icons in packages/ui/src/icons/:

    • Each icon has its own folder with index.tsx + index.css
  3. Compare Figma design to available icons:

    • Does the design use icons not currently in the component?
    • Does the design use icons that don't exist yet?
  4. Document findings:

    • Existing & used: No action needed
    • Existing but not imported: Will need to add import
    • Missing from codebase: Flag for user — need to source/create icon

Figma Icons Source:

When updating or creating icons, reference the Figma icon library at:

~/figma/figma/fpl/icons/src/icons/

Icon naming convention: icon-{size}-{name}.tsx (e.g., icon-16-close.tsx, icon-24-chevron-down.tsx)

To find the correct icon:

  1. Note the icon name from Figma design (e.g., "close", "chevron-down")
  2. Check both 16px and 24px variants if they exist
  3. Read the corresponding files and extract the SVG paths for each size

Icon implementation rules:

  1. Props: Icon components MUST accept these props (keep existing props when updating):

    type IconProps = {
      readonly className?: string
      readonly size?: 16 | 24 // Add more sizes as needed
      // ... keep any existing component-specific props
    }
    
  2. Multi-size support: Store path data keyed by size:

    const paths = {
      16: 'M4.854 4.146...', // from icon-16-{name}.tsx
      24: 'M6.854 6.146...', // from icon-24-{name}.tsx
    }
    
  3. SVG rendering: Use the size prop to select path and viewBox:

    <svg width={size} height={size} viewBox={`0 0 ${size} ${size}`} fill="none">
      <path d={paths[size]} fill="currentColor" />
    </svg>
    

Read the full file on GitHub · 646 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. 1mo ago Changed · +25 tokens per session 0eb129800c6b
  2. 1mo ago First seen · 646 lines · 0 tokens per session scan A 827f5ac0acd4

Subscribe to this mod's changes

ui4 is a skill published in the GitHub repository payloadcms/payload (45,565 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 6,035 once invoked, about $0.0001 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 2026-08-30.