agentmods.dev

portal-branding

portal-branding is a skill for Claude Code from Kong/ai-marketplace. It costs 43 tokens per session (1,574 once invoked), scanned A, original, MIT.

A design guide for matching a brand or existing website on Kong Konnect Dev Portal pages. Kong Konnect is Kong's platform for managing APIs and related developer tools.

In plain words
What is it for?
Use it to brand one or more developer-portal pages and reproduce a reference site's visual appearance with portal components.
Why use it?
It helps keep portal pages visually consistent by guiding the use of colors, fonts, images, spacing, and page styling.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kong-konnect plugin — 22 skills, 1 MCP server shipped together

not rated 6repo 10d ago A scan 43 tokens original MIT

Good fit Use it to brand one or more developer-portal pages and reproduce a reference site's visual appearance with portal components.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kong/ai-marketplace/portal-branding
View source ↗ Kong/ai-marketplace konghq.com
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.

Any agent
npx skills add Kong/ai-marketplace --skill portal-branding
Clone the repo
git clone --depth 1 https://github.com/Kong/ai-marketplace

Made for: Claude Code.

Or install kong-konnect, the plugin that ships this one along with the rest of its 22 skills, 1 MCP server.

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 portal-branding

README.md
[![agentmods](https://agentmods.dev/badge/skills/kong/ai-marketplace/portal-branding/github.svg)](https://agentmods.dev/skills/kong/ai-marketplace/portal-branding)
Your own site
<a href="https://agentmods.dev/skills/kong/ai-marketplace/portal-branding"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/portal-branding/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 portal-branding

Your own site · 80×15
<a href="https://agentmods.dev/skills/kong/ai-marketplace/portal-branding"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/portal-branding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,574 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 $0.00043 $0.01574
Opus 5.5 $0.00017 $0.00630
Sonnet 5.5 $0.00009 $0.00315
Haiku 4.5 $0.00004 $0.00157

Measured 2mo ago against content hash e91fdf0bf9b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

portal-branding 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 2mo 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.

plugins/kong-konnect/skills/portal-branding/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Konnect Dev Portal page branding

Goal

Reproduce a brand or an existing website's look on Dev Portal MDC pages: colors, fonts, imagery, and spacing, through MDC components and page-level styling. Work in MDC page files, locally or in a repo. Do not push destructive changes to a live portal through the Konnect API unless the user explicitly asks.

Clarify First

Ask two or three high-impact questions, each with a default to confirm; do not interrogate:

  • source to match: a URL or short brand description
  • target page or pages
  • which details must be exact, which can be approximate
  • light or dark base

Tool Selection

  • Author, format, validate, and preview MDC with the portal-page-design toolchain, which uses the Konnect MCP server for verified components, design tokens, validation, and preview. This skill adds the brand-specific steps below.
  • If the MCP server is not connected, recommend connecting it. Without it there is no preview or parity loop: work from general MDC knowledge and the user's files, ask them to preview in the Portal Editor, and say plainly the result is less reliable.
  • Capturing the source and comparing results need a browser. If no browser automation (Playwright or an agent browser) is available, have the user install one first.
  • If a local preview extension is available, use it for live preview while editing.

Workflow

  1. Confirm the source (URL or brand cues) and target MDC page.
  2. Capture the brand cues (see Capture the brand).
  3. Build the look with components and page-level styling (see Apply the brand).
  4. Preview and compare to the source across widths, then iterate (see Parity loop).
  5. Check contrast against every background.
  6. Report what matched; for anything the page cannot express, offer a concrete alternative, not a silent miss.

Capture the brand

Aim for a small set of concrete cues, not a pile of screenshots:

  1. Brand and accent colors: dominant non-neutral colors on primary buttons, links, and highlights. Record hex.
  2. Base tone: light or dark.
  3. Typography: heading, body, and monospace fonts, plus the weights used.
  4. Imagery: logos, icons, and hero images with source URLs. Prefer SVG.
  5. Spacing and shape: dense or airy, plus corner-radius and border feel.

Read the full file on GitHub · 164 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. 2mo ago First seen · 164 lines · 43 tokens per session scan A e91fdf0bf9b0

Subscribe to this mod's changes

portal-branding is a skill published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 1,574 once invoked, about $0.0002 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 2026-08-31.

Design and UXagent-skillsagentic-workflowsagentsaikongkong-gateway
Related

portal-branding compared with skills from other repositories

portal-branding next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
portal-brandingKong/ai-marketplaceSkill610d agoMITA43Claude Code
surfsense-htmlMODSetter/SurfSenseSkill17kyesterdayApache-2.0A89Claude Code, Codex
show-mehumanlayer/humanlayerSkill13kyesterdayApache-2.0A25Claude Code
frontend-ui-dark-tsmicrosoft/skillsSkill3.2kyesterdayMITA48Claude Code
dxfearthtojake/text-to-cadSkill26k2d agoMITC120Claude Code, Codex
decocms-uidecocms/studioSkill415yesterdayMITA95Claude Code
drag-panemarcus/sidecarSkill1.1k29d agoMITA70Claude Code