konnect-app-auth

konnect-app-auth is a skill for Claude Code from Kong/ai-marketplace. It costs 45 tokens per session (1,342 once invoked), scanned A, original, MIT.

A workflow for application authentication in the Kong Konnect developer portal, where developers register applications and obtain credentials to use published APIs. It covers authentication strategies, approvals, registrations, and the path from publication to enforcement.

In plain words
What is it for?
Use it to choose or troubleshoot application-auth strategies, configure registrations and approvals, inspect credentials, and verify that published APIs enforce the intended app-auth setup.
Why use it?
It helps diagnose cases where an API is already published but developers cannot register, get credentials, or access it. It keeps portal sign-in and general API publication issues separate.

Skill for Claude Code

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

Part of the kong-konnect plugin — 21 skills shipped together

Good fit Use it to choose or troubleshoot application-auth strategies, configure registrations and approvals, inspect credentials, and verify that published APIs enforce the intended app-auth setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kong/ai-marketplace/konnect-app-auth
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-app-auth
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 21 skills.

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-app-auth

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kong/ai-marketplace/konnect-app-auth"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-app-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,342 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 $0.00045 $0.01342
Opus 5 $0.00023 $0.00671
Sonnet 5 $0.00009 $0.00268
Haiku 4.5 $0.00005 $0.00134

Measured 11d ago against content hash d161bd203c2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

konnect-app-auth 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 11d 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-app-auth/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Konnect application auth workflow

Goal

Help an operator configure or troubleshoot how developers register applications, receive credentials, and use APIs through Konnect Dev Portal and Konnect Application Auth.

Own the application-auth branch only: strategy choice, application registration, approvals, credentials, and the publication-to-enforcement path. Do not keep Portal sign-in, SSO, or generic API publication diagnosis in this skill after the surface is classified.

Tool Selection

  • Use the shared kong-konnect MCP server first for live inspection of portals, publications, application auth strategies, applications, registrations, and related approvals.
  • Preserve the repository's chosen declarative toolchain when auth resources need to change: use terraform-konnect for HCL-managed resources and kongctl-declarative only when the surrounding repo already uses kongctl for this Konnect workflow.
  • Use deck-gateway only when the real change is downstream Gateway-entity config rather than Portal app-auth configuration.
  • If live Konnect state matters and kong-konnect MCP is not connected, say so early and continue with user-provided artifacts or repo context.
  • If the primary issue is developer sign-in, SSO, or broad org/team access, classify that early and stop instead of debugging app credentials here.

References To Load

Load only the reference file that matches the active branch:

  • references/auth-strategy-selection.md
    • Load when choosing between key auth, self-managed OIDC, and DCR is the main decision.
  • references/registration-and-approval-flows.md
    • Load when the strategy is plausible but self-service, approvals, or registration state still block developers.
  • references/linked-service-and-enforcement.md
    • Load when the hard question is whether auth can actually be enforced on the linked Gateway Service path.

Inspection Order

1. Classify the failing surface before choosing fixes

Clarify whether the problem is:

Read the full file on GitHub · 168 lines

Files

What ships with it

3 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. 11d ago First seen · 168 lines · 45 tokens per session scan A d161bd203c2a

Subscribe to this mod's changes

konnect-app-auth is a skill published in the GitHub repository Kong/ai-marketplace (5 stars, last pushed 21d ago), licensed MIT. It adds 45 tokens to every session and 1,342 once invoked, about $0.0002 per session on Opus 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

Other skills, from other repositories

agent-communication-protocol

Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.

majiayu000/claude-skill-registry · 25 tokens

API Discoverability for Agents

Making self-hosted services agent-discoverable — bake in a machine-readable API description (OpenAPI spec or a minimal API.md) when building, and discover-first (spec paths, repo search) before probing when integrating.

niels-emmer/myace · 51 tokens

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

cqrs-implementation

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

wshobson/agents · 35 tokens

workflow-orchestration-patterns

Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.

wshobson/agents · 49 tokens

microservices-patterns

Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.

wshobson/agents · 38 tokens