agentmods.dev

konnect-reference-platform

konnect-reference-platform is a skill for Claude Code from Kong/ai-marketplace. It costs 31 tokens per session (1,927 once invoked), scanned A, original, MIT.

A workflow for designing or modernizing a federated Kong Konnect reference platform across repositories. Kong Konnect is a platform for managing APIs and related gateway resources; the workflow keeps checked-in configuration as the intended source of truth.

In plain words
What is it for?
Use it to plan, implement, or review shared Konnect platform architecture, resource ownership, and deployment promotion.
Why use it?
It clarifies ownership and promotion across repositories while avoiding an extra configuration format or wrapper around Kong's supported tools.

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 changed 9d ago A scan 31 tokens original MIT

Good fit Use it to plan, implement, or review shared Konnect platform architecture, resource ownership, and deployment promotion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kong/ai-marketplace/konnect-reference-platform
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 konnect-reference-platform
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 konnect-reference-platform

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kong/ai-marketplace/konnect-reference-platform"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-reference-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,927 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 $0.00031 $0.01927
Opus 5.5 $0.00012 $0.00771
Sonnet 5.5 $0.00006 $0.00385
Haiku 4.5 $0.00003 $0.00193

Measured 9d ago against content hash fee6ef8eabca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

konnect-reference-platform 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.

plugins/kong-konnect/skills/konnect-reference-platform/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Konnect reference platform

Goal

Design, implement, or review a maintained Konnect reference architecture and a working example that teams can read, copy, and adapt.

Keep the platform declarative and federated. Do not invent a registry, wrapper CLI, or second configuration format over supported Kong tooling.

Tool Selection

  • Treat the repository manifests as intended state. Use live Konnect state to inspect or prove deployment, not as a replacement source of truth.
  • Use kongctl-declarative for Konnect platform resources such as teams, access, control planes, Catalog APIs, versions, specs, implementations, publications, Portals, and application auth strategies.
  • Use deck-gateway for Gateway Services, Routes, and plugins. Prefer OpenAPI-driven generation when a service contract is the starting point.
  • Preserve an existing Terraform architecture if the target repository already owns these resources in Terraform. This skill describes the ownership model; it does not require a tool migration.
  • Use the shared kong-konnect MCP server when current live state matters. If it is unavailable, continue from checked-in manifests and clearly separate intended architecture from live proof.

References To Load

  • Load references/ownership-and-promotion.md when defining repository boundaries, CI identities, development ownership, or production promotion.

For the maintained public implementation, consult the official Reference Platform documentation and the KongAirlines repositories. Prefer their current checked-in manifests over historical prose or examples that use unsupported tools.

Workflow

1. Establish the sources of truth

Find the checked-in kongctl manifests, decK files, OpenAPI contracts, and CI workflows before proposing structure.

Require these properties unless the user deliberately chooses another model:

  • no custom registry or generated orchestration format
  • one default branch with distinct development and production resources
  • a root beta OpenAPI contract that advances for every contract change, plus immutable, stable versioned files
  • an explicit current-production version in the production Catalog manifest
  • generated decK files committed so reviewers can inspect exact Gateway state
  • append-only Catalog API versions, created with a separate kongctl apply manifest and omitted from manifests reconciled with kongctl sync

Read the full file on GitHub · 208 lines

Files

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.

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 Changed · +4 lines fee6ef8eabca
  2. 18d ago Changed · +19 lines 70fe97594a81
  3. 28d ago First seen · 185 lines · 31 tokens per session scan A 9f1f4c7f9d0a

Subscribe to this mod's changes

konnect-reference-platform is a skill published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 31 tokens to every session and 1,927 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 2026-10-10.

Backend and APIsCloudDevOps and cloudagent-skillsagentic-workflowsagentsaikongkong-gateway
Related

konnect-reference-platform compared with skills from other repositories

konnect-reference-platform next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
konnect-reference-platformKong/ai-marketplaceSkill610d agoMITA31Claude Code
sandbox-stablecloudflare/skillsSkill3.3kyesterdayApache-2.0A39Claude Code
azure-eventhub-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA94Claude Code
azure-mgmt-apimanagement-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA97Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
azure-servicebus-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA86Claude Code
sandbox-nextcloudflare/skillsSkill3.3kyesterdayApache-2.0A39Claude Code