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 agentmods add skills/arjunprabhulal/devops-skills/api-gatewaynpx skills add arjunprabhulal/devops-skills --skill api-gatewaygit clone --depth 1 https://github.com/arjunprabhulal/devops-skillsWrote 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/arjunprabhulal/devops-skills/api-gateway)<a href="https://agentmods.dev/skills/arjunprabhulal/devops-skills/api-gateway"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/api-gateway.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.01282 |
| Opus 5 | $0.00056 | $0.00641 |
| Sonnet 5 | $0.00023 | $0.00256 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
api-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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Gateway
An API gateway earns its place by centralizing the things every backend would otherwise reimplement badly: authentication, rate limiting, and a stable external contract in front of services that change internally all the time. It only pays for itself when it stays a thin, well-understood layer — the moment it accumulates business logic, it becomes a second application nobody wants to own, deployed on a critical path everything else depends on.
The gateway is infrastructure, not a place to write features. Every rule it enforces should be cross-cutting; anything specific to one backend belongs in that backend.
1. Route by contract, not by convenience
The gateway's routing table is the external API's actual shape — clients depend on it staying stable even as internal services are renamed, split, or replaced behind it. Decide routing rules (path, host, header) up front as a deliberate contract, not as whatever happened to match during initial setup, because changing that contract later is a breaking change for every client.
- Version the external contract explicitly (
/v1/, a header, or a distinct host) so internal refactors never force every client to change at once. - Keep the mapping from external route to internal service in one place, reviewable as a unit, not scattered across per-team gateway plugins.
Done when: an internal service can be renamed or split without any external client noticing.
2. Centralize auth, but don't let the gateway become the source of truth for identity
The gateway is the right place to enforce "is this request authenticated" once instead of in every backend — validating a token's signature and expiry is exactly the kind of cross-cutting check that belongs at the edge. It is the wrong place to own user identity or session state; that stays in an identity provider, with the gateway only checking, not issuing or storing.
- Validate tokens at the gateway, and pass identity downstream as a verified header or claim so backends don't re-implement token parsing.
- Never let the gateway silently downgrade auth failures to "allow" on a validation error — fail closed, not open.
- Full identity and authorization policy design lives in
iam-access-management; the gateway enforces decisions, it doesn't define them.
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.
- 4d ago First seen · 104 lines · 113 tokens per session scan A 6e875930e60f
api-gateway is a skill published in the GitHub repository arjunprabhulal/devops-skills (2 stars, last pushed 10d ago), licensed MIT. It adds 113 tokens to every session and 1,282 once invoked, about $0.0006 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
google-mobile-ads-android-migrate-to-next-gen
Migrates Android applications from the old, legacy Google Mobile Ads (GMA) SDK (com.google.android.gms:play-services-ads) to the new GMA Next-Gen SDK (com.google.android.libraries.ads.mobile.sdk:ads-mobile-sdk). Provides comprehensive mapping tables for imports, classes, and method signatures to help determine…
agent-platform-inference
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling…
agent-platform-deploy
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a…
agent-platform-eval-flywheel
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
agent-platform-alert-configuration
Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. Don't use for standard…