Borrowing it
Nothing to install: this file belongs to Aviator-Coding/home-ops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Aviator-Coding/home-ops/main/.agents/skills/agentgateway/SKILL.mdgit clone --depth 1 https://github.com/Aviator-Coding/home-opsWrote 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/aviator-coding/home-ops/agentgateway)<a href="https://agentmods.dev/skills/aviator-coding/home-ops/agentgateway"><img src="https://agentmods.dev/badge/skills/aviator-coding/home-ops/agentgateway/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/aviator-coding/home-ops/agentgateway"><img src="https://agentmods.dev/badge/skills/aviator-coding/home-ops/agentgateway.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 | $0.00090 | $0.01324 |
| Opus 5.5 | $0.00036 | $0.00530 |
| Sonnet 5.5 | $0.00018 | $0.00265 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade A, and why
agentgateway 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 25d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentgateway: routes, listeners, backends and failover
Standalone AgentGateway in namespace ai, API group agentgateway.dev/v1alpha1.
Chart and CRDs are oci://ghcr.io/agentgateway/charts/agentgateway{,-crds}
(tag in app/ocirepository.yaml and crds/ocirepository.yaml). Not
cr.agentgateway.dev, and not the retired kgateway-bundled chart. MCP is
ToolHive, not this gateway. LiteLLM is a separate governance layer and is
never this gateway's /v1. Skill litellm-proxy.
Tripwires
- An
httplistener with no auth policy is an open door to the paid backends. Gateway API path matching is most-specific-wins, sotls-redirect's/never sees/v1.internalmust stay https-only.public's http listener is the one exception, and only becauseapikey-policyis bound to that listener. gateways-auth.md internal-noauthstaysClusterIP. It is the keyless surface (http://internal-noauth.ai.svc.cluster.local/v1). A LoadBalancer would publish it on the LAN. The type comes from that Gateway's ownAgentgatewayParameters, which merge with the class-level parameters rather than replace them. Gate:scripts/ci/agentgateway-exposure-test.py.- The groq rule stays above the vendor-slug catch-all. Its family regex
also matches OpenRouter
moonshotai/...slugs. Every other unified-route regex is mutually exclusive, so order is not load-bearing except here. routing-backends.md - Failover needs a health policy and a
/v1path.llm-chat-failover-healthmust target the failover backend (response.code >= 500 || response.code == 429, eviction after 2 failures). Without it, providers are never evicted. A backendpathPrefixreplaces the default/v1and must include/v1, or the upstream returns its website. - A new model needs three edits: a rule in
httproute-unified.yamlwhen the family is new, a price row inrules/cost.yaml, and a catalog entry inhttproute-models.yaml. Re-enabling a dormant backend (zai, togetherai, opencodeai) is one new rule. Clients send provider-native ids; nothing rewrites them. - The TLS ExternalSecret is never
CreatedOnce. That policy syncs once and then reports Ready while the certificate expires. The bootstrap seed undernetwork/certificates/importkeepsCreatedOnceand is a different object. This one refreshes (refreshInterval: 1h). - Never reference
response.bodyin a tracing CEL expression. Agentgateway buffers a body only when an expression references it. Buffering the response breaks token streaming. Request-body capture on/chat/completionsis the allowed one. observability.md - None of the three Gateways publish DNS. They carry
external-dns.alpha.kubernetes.io/controller: none. The LAN wildcard*.${SECRET_DOMAIN} -> 10.50.0.27is a hand-made UniFi record (no registry TXT twin). external-dns will not delete it. Skillnetworking. - Keep the CRD HelmRelease. The data-plane chart does not install
CRDs. Deleting
agentgateway-crdsdrops the kinds the routes need.
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.
- 25d ago First seen · 87 lines · 90 tokens per session scan A 7bdd2571cf88
agentgateway is a skill published in the GitHub repository Aviator-Coding/home-ops (3 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 1,324 once invoked, about $0.0004 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 2026-09-29.
Other skills, from other repositories
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
websocket-engineer
Use when building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room management.
azure-eventhub-dotnet
Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
aws-blocks
Guides building full-stack applications with AWS Blocks — an Infrastructure-from-Code framework. Applies when creating APIs, selecting Building Blocks (KVStore, DistributedTable, Database, AuthBasic, AuthCognito, Realtime, AsyncJob, FileBucket, etc.), running local development, or deploying AWS Blocks applications.…