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 deck-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/deck-gateway)<a href="https://agentmods.dev/skills/kong/ai-marketplace/deck-gateway"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/deck-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/deck-gateway"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/deck-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 | $0.00060 | $0.02165 |
| Opus 5 | $0.00030 | $0.01082 |
| Sonnet 5 | $0.00012 | $0.00433 |
| Haiku 4.5 | $0.00006 | $0.00216 |
Grade A, and why
deck-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 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
decK gateway workflows
Goal
Generate, inspect, and apply Kong Gateway entity configuration with decK
without losing track of live state, scope, or deployment model.
Use this skill for Gateway entities and Gateway-oriented GitOps. Do not use it
as a replacement for Konnect platform workflows that belong in kongctl or
Terraform.
Tool Positioning
- Use the shared
kong-konnectMCP server first for live Konnect inspection when the target Gateway entities live in Konnect and MCP is available. - Use this skill when the repository already uses
decK,_format_version, ordeck gatewaycommands, or when the user explicitly asks fordecK. - Use a domain skill or
kongctl-queryfirst when the real task is incident diagnosis, live-state discovery, or Konnect inspection before a repo-owneddecKslice is identified. - Preserve the existing
decKlayout, file split, tags, and CI patterns in the repository. - Do not convert a Terraform or
kongctlrepository todecKunless the user explicitly asks for that migration. - Hand off to
terraform-kong-gateway,terraform-konnect, orkongctl-declarativewhen the user wants HCL orkongctlrather thandecK.
References To Load
Load only the reference file that matches the active branch:
references/command-paths.md- Load when choosing between validate, diff, sync, dump, or file-generation paths.
references/openapi-generation.md- Load when the user is starting from an OpenAPI document and wants Gateway entities derived from it.
references/state-shaping-and-tags.md- Load when file split, tags, include boundaries, or ownership shape matters more than the entity content itself.
references/dump-diff-sync-safety.md- Load when the main question is how to inspect live state safely before mutating it.
Validation Contract
Preflight
Before editing files or proposing a live sync:
- Confirm
deckis installed and runnable:deck version - Confirm the target deployment model and live target:
- self-managed Gateway via Admin API
- Konnect-managed control plane via the appropriate Konnect auth flags
- Confirm credentials are already available through environment variables, config files, or secure host settings. Never echo or commit secrets.
- Inspect the current file structure before writing new files.
- Confirm the ownership boundary:
- which state file, directory, include path, or wrapper script is in scope
- whether tags are used to scope ownership
- which environment or control plane the commands should touch
- Confirm whether the task is declarative authoring, preview, export, or live
mutation before choosing a
decKpath.
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.
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.
- 11d ago First seen · 246 lines · 60 tokens per session scan A 253379a2aa2a
deck-gateway is a skill published in the GitHub repository Kong/ai-marketplace (5 stars, last pushed 21d ago), licensed MIT. It adds 60 tokens to every session and 2,165 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.