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 oxy-hq/oxygen --skill oxy-custom-appsgit clone --depth 1 https://github.com/oxy-hq/oxygenWrote 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/oxy-hq/oxygen/oxy-custom-apps)<a href="https://agentmods.dev/skills/oxy-hq/oxygen/oxy-custom-apps"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-custom-apps/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/oxy-hq/oxygen/oxy-custom-apps"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-custom-apps.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 | $0.00220 | $0.05655 |
| Opus 5.5 | $0.00088 | $0.02262 |
| Sonnet 5.5 | $0.00044 | $0.01131 |
| Haiku 4.5 | $0.00022 | $0.00566 |
Grade A, and why
oxy-custom-apps 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 yesterday.
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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom-app development
Custom-app bundles are arbitrary JS apps served by Oxy at
https://<env>/customer-apps/<org>/<slug>/. Oxy is a data gateway:
serves static assets, gates cookie auth, and proxies queries. The
bundle is opaque above the data plane — no per-app server config.
This file is the contract. The detail lives in references/ — see
Read next for which file answers what.
The Oxy App Kit (use it)
Two small packages remove the footguns — default to them rather than wiring a bundle by hand:
@oxy-hq/sdk— the data layer (useQuery,useSemanticQuery,useAgentRun,<OxyChat>); see rule 2 and the@oxy-hq/sdkREADME.@oxy-hq/vite-plugin(oxyApp()invite.config.ts) — bakes the asset base path from the manifest, copiesoxy-app.jsonintoout/, proxies/apiin dev, and injects thewindow.__OXY_APP__shim. Dropping it re-introduces the #1 bug — asset 404s → blank dashboard (rule 3).
Scaffold both with pnpm create @oxy-hq/oxy-app my-app (templates vite — the
default — functions, dashboard, single-store; -t functions adds Oxy
Functions). The platform is kit-agnostic (any bundle with a correct base path
works), but hand-rolling means owning the base-path + dev-proxy wiring yourself.
Three rules
-
oxy-app.json(project root, notpublic/) is identity only. Schema:{ "schemaVersion": 2, "slug": "url-slug", "orgSlug": "your-org", "name": "Display Name" }Required:
schemaVersion(must be2),slug(non-empty). Strongly recommended:orgSlug(lets@oxy-hq/vite-pluginderive the asset base path automatically, so plainpnpm buildproduces a bundle ready to drop into the linked org with no env var). Optional:name(display),projectId(dev-time hint).At serve time, oxy injects the authoritative org + project from the admin row via
window.__OXY_APP__— the manifest'sorgSlugandprojectIdare advisory hints only, never enforcement.
What ships with it
5 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.
- yesterday Changed · -163 lines · +150 tokens per session 98a5976f7056
- 2d ago First seen · 548 lines · 70 tokens per session scan A 7fdfe8586f1b
oxy-custom-apps is a skill published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 220 tokens to every session and 5,655 once invoked, about $0.0009 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 2026-10-14.
Other skills, from other repositories
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
subscriptions
Set up real-time event streams with async generator subscriptions using .subscription(async function() { yield }). SSE via httpSubscriptionLink is recommended over WebSocket. Use tracked(id, data) from @trpc/server for reconnection recovery with lastEventId. WebSocket via wsLink and createWSClient from @trpc/client…
links
Configure the tRPC client link chain: httpLink, httpBatchLink, httpBatchStreamLink, splitLink, loggerLink, wsLink, createWSClient, httpSubscriptionLink, unstablelocalLink, retryLink. Choose the right terminating link. Route subscriptions via splitLink. Build custom links for SOA routing. Link options: url, headers…
middlewares
Create and compose tRPC middleware with t.procedure.use(), extend context via opts.next({ ctx }), build reusable middleware with .concat() and .unstablepipe(), define base procedures like publicProcedure and authedProcedure. Access raw input with getRawInput(). Logging, timing, OTEL tracing patterns.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.