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/datatorag/mcp-gateway/gateway-devnpx skills add datatorag/mcp-gateway --skill gateway-devgit clone --depth 1 https://github.com/datatorag/mcp-gatewayWrote 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/datatorag/mcp-gateway/gateway-dev)<a href="https://agentmods.dev/skills/datatorag/mcp-gateway/gateway-dev"><img src="https://agentmods.dev/badge/skills/datatorag/mcp-gateway/gateway-dev.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 | $0.00050 | $0.03724 |
| Opus 5 | $0.00025 | $0.01862 |
| Sonnet 5 | $0.00010 | $0.00745 |
| Haiku 4.5 | $0.00005 | $0.00372 |
Grade A, and why
gateway-dev 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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gateway Dev
Before you start
Load the codebase-map skill first — this skill assumes you already know the request flow, the two plugin-manager.ts files, and the invariants list. It doesn't repeat any of that; it's recipes only.
Recipes
Add an API route (dashboard-authenticated)
Dashboard endpoints live under apps/gateway/src/app/api/**/route.ts and reuse the shared wrapper rather than hand-rolling auth:
- Create
route.ts, exportdynamic = "force-dynamic"if the response must never be statically cached (every existing usage route does this). - Wrap the handler in
withRoute(apps/gateway/src/lib/with-route.ts, replacedwith-rate-limit.tsin the DRY-1 refactor) — it resolves the session viagetSessionUserId(apps/gateway/src/lib/session.ts), 401s{error:"Unauthorized"}if absent, checksdashboardApiLimiter(apps/gateway/src/gateway/usage/rate-limit.ts) → 429, and maps any unhandled throw to a generic 500 vialogAndGenericError(apps/gateway/src/lib/errors.ts) so a rawError.messagenever reaches a client. Handler shape is(userId, req, ctx) => Promise<Response>; for[slug]routes pass the ctx type:withRoute<{ params: Promise<{slug: string}> }>(...). Every session-gated JSON route uses it — the only exceptions are the two OAuth connect/callback redirect flows (bespoke CSRF-cookie handling). - Query through
db(apps/gateway/src/lib/db.ts), not a freshcreateDb()call. - Return
NextResponse.json(...). Seeapps/gateway/src/app/api/usage/summary/route.tsfor the full shape (session → rate limit → drizzle aggregate query → JSON):
export const dynamic = "force-dynamic";
export const GET = withRoute(async (userId) => {
const rows = await db.select({ /* ... */ }).from(usageEvents)
.where(eq(usageEvents.userId, userId));
return NextResponse.json({ /* ... */ });
});
Add an API route (public, unauthenticated)
For public-facing endpoints (lead capture, webhooks) follow apps/gateway/src/app/api/leads/route.ts instead: its own dedicated limiters (leadsMinuteLimiter/leadsHourLimiter in apps/gateway/src/gateway/leads/limiter.ts, same createRateLimiter primitive as dashboardApiLimiter), a zod bodySchema with a honeypot field, and IP hashing (createHash("sha256") salted with LEADS_IP_SALT from getEnv()) instead of storing raw IPs. Client IP comes from CF-Connecting-IP first (prod is behind Cloudflare with the origin firewalled to CF ranges); the leftmost X-Forwarded-For entry is client-spoofable and only a dev fallback — any new public endpoint must use the same order.
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.
- 3d ago First seen · 108 lines · 50 tokens per session scan A cb02832776cc
gateway-dev is a skill published in the GitHub repository datatorag/mcp-gateway (3 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 3,724 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…