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.
npx skills add Kong/ai-marketplace --skill konnect-ai-gatewaygit clone --depth 1 https://github.com/Kong/ai-marketplaceWrote 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.
[](https://agentmods.dev/skills/kong/ai-marketplace/konnect-ai-gateway)<a href="https://agentmods.dev/skills/kong/ai-marketplace/konnect-ai-gateway"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-ai-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.
<a href="https://agentmods.dev/skills/kong/ai-marketplace/konnect-ai-gateway"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-ai-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01598 |
| Opus 5 | $0.00028 | $0.00799 |
| Sonnet 5 | $0.00011 | $0.00320 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
konnect-ai-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Konnect AI Gateway triage
Goal
Diagnose the narrowest Konnect AI Gateway failure layer across request path, provider targeting, AI policy, and AI-runtime visibility.
Use this skill for AI Gateway operator workflows, not for generic prompt-engineering, provider SDK debugging, or model-quality evaluation.
Tool Selection
- Use the shared
kong-konnectMCP server first for live inspection of control planes, Gateway entities, and LLM analytics surfaces. - Prefer LLM-specific analytics when the user is asking about token usage, latency, or AI request health. Use the LLM analytics MCP/query surface when AI-runtime data is the real question rather than generic API analytics.
- Preserve the repository's chosen declarative toolchain for implementation:
deck-gatewayfor Gateway-entity GitOps,terraform-konnectfor HCL-managed Konnect AI Gateway resources,terraform-kong-gatewayfor self-managed HCL, andkongctl-declarativeonly when the surrounding Konnect repo already uses that path. - If live Konnect state matters and
kong-konnectMCP is not connected, say so early and continue with repo config or user-provided artifacts. - Hand off early to
konnect-gateway-triagewhen the blocker is generic gateway reachability, rollout, or route/service health rather than an AI-specific layer.
References To Load
Load the first matching reference. Do not load all three by default:
references/provider-routing.md- Load when the main question is model/provider selection, route targeting, fallback, or provider-specific request behavior.
references/guardrails-and-policy-intent.md- Load when traffic works technically but policy intent, prompt shaping, or governance behavior looks wrong.
references/observability-and-cost-signals.md- Load when the question is about tokens, latency, AI-specific analytics, or operational visibility rather than request construction.
Inspection Order
1. Classify the report before choosing a layer
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.
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.
- 12d ago First seen · 199 lines · 57 tokens per session scan A 554ec4f21ca6
konnect-ai-gateway is a skill published in the GitHub repository Kong/ai-marketplace (5 stars, last pushed 22d ago), licensed MIT. It adds 57 tokens to every session and 1,598 once invoked, about $0.0003 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.
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.
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.
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.
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.
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.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.