konnect-event-gateway

konnect-event-gateway is a skill for Claude Code from Kong/ai-marketplace. It costs 52 tokens per session (1,412 once invoked), scanned A, original, MIT.

A troubleshooting workflow for Kong Konnect Event Gateway, which handles event requests through listeners, hostnames, virtual clusters, backend clusters, authentication, and policies. It follows a request through those parts in order.

In plain words
What is it for?
Use it to inspect listeners, hostname mappings, virtual and backend clusters, authentication, policy decisions, and the request path from client to backend.
Why use it?
It helps locate the exact step where an Event Gateway request fails. It avoids applying assumptions from standard API gateways to this event-specific routing model.

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

Good fit Use it to inspect listeners, hostname mappings, virtual and backend clusters, authentication, policy decisions, and the request path from client to backend.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kong/ai-marketplace/konnect-event-gateway"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-event-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,412 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 $0.00052 $0.01412
Opus 5.5 $0.00021 $0.00565
Sonnet 5.5 $0.00010 $0.00282
Haiku 4.5 $0.00005 $0.00141

Measured 2mo ago against content hash 3ef5adc7b6cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

konnect-event-gateway 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/konnect-event-gateway/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Event Gateway operator workflow

Goal

Troubleshoot Event Gateway using its own entity model instead of forcing it into standard gateway assumptions.

Default to following the request path end to end: client -> listener -> virtual cluster -> backend cluster -> policy and auth

Own the diagnosis of the failing Event Gateway hop. Hand off implementation or non-Event-Gateway platform problems once that hop is clear.

Tool Selection

  • Use the shared kong-konnect MCP server first for live Event Gateway inspection.
  • Use kongctl-query for read-only resource checks and concise summaries where the CLI surface is available.
  • Preserve the repository's chosen declarative toolchain when Event Gateway resources need to change. Prefer kongctl-declarative for kongctl YAML and terraform-konnect when the required Event Gateway resources are already managed in HCL.
  • Hand off early to konnect-gateway-triage when the blocker is generic control-plane, data-plane, or rollout health rather than Event Gateway path semantics.
  • If live Konnect state matters and kong-konnect MCP is not connected, say so early and continue with CLI or user-provided artifacts.

Do not reuse generic gateway triage blindly. Event Gateway deserves a dedicated inspection order because the operator objects differ.

References To Load

Load only the reference file that matches the active branch:

  • references/event-path-map.md
    • Load when the operator only has a symptom and you need to map the failing hop across listener, virtual cluster, backend cluster, auth, and policy.
  • references/listener-and-hostname-mapping.md
    • Load when the likely issue is listener reachability, hostname mapping, TLS, or protocol assumptions.
  • references/cluster-routing-boundaries.md
    • Load when virtual-cluster to backend-cluster routing intent is the hard part.
  • references/auth-and-policy-order.md
    • Load when clients connect but get denied, rewritten, or otherwise fail after reachability is already proven.

Read the full file on GitHub · 191 lines

Files

What ships with it

4 files 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. 2mo ago First seen · 191 lines · 52 tokens per session scan A 3ef5adc7b6cb

Subscribe to this mod's changes

konnect-event-gateway is a skill published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 52 tokens to every session and 1,412 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.

Related

konnect-event-gateway compared with skills from other repositories

konnect-event-gateway next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
konnect-event-gatewayKong/ai-marketplaceSkill610d agoMITA52Claude Code
eveComposioHQ/composioSkill31kyesterdayMITA47Claude Code, Codex
azure-messagingmicrosoft/skillsSkill3.2kyesterdayMITA178Claude Code
database-rds-devopsaws/tools-for-devops-agentSkill137yesterdayApache-2.0A75Claude Code, Codex
iii-observeiii-hq/iiiSkill19kyesterdaynoneA66Claude Code, Codex
iii-error-handlingiii-hq/iiiSkill19kyesterdaynoneA47Claude Code, Codex
guardrails-developer-guideNVIDIA-NeMo/GuardrailsSkill7.4kyesterdaynoneA92Claude Code, Codex