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/val-town/plugins/oauthnpx skills add val-town/plugins --skill oauthgit clone --depth 1 https://github.com/val-town/pluginsWhat 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 | $0.00083 | $0.01035 |
| Opus 5 | $0.00042 | $0.00517 |
| Sonnet 5 | $0.00017 | $0.00207 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
oauth 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 2d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OAuth (std/oauth)
Val Town provides zero-config "Log in with Val Town" via std/oauth. No database setup, no provider config — wrap your Hono fetch handler and you get login, logout, and session management for free. Sessions are stored in encrypted cookies and last 30 days.
This is for Val Town account login only. For Google / GitHub / Slack / etc. OAuth, see the third-party-integrations skill — those flows are documented per-service.
If the goal is to keep an app internal to a team rather than to give it its own logged-in users, restricting the val's app access is the simpler answer — the platform gates the endpoint before your code runs, and you write no auth code. See the restricted-access skill. Don't apply both to one val: a restricted val that also runs oauthMiddleware makes visitors authenticate twice.
Imports
import {
getOAuthUserData,
oauthMiddleware,
} from "https://esm.town/v/std/oauth/middleware.ts";
Wrapping your app
oauthMiddleware(handler) takes your Hono fetch handler and returns a wrapped handler that injects three auto-managed routes:
GET /auth/login— starts the login flowGET /auth/callback— completes the login flowPOST /auth/logout— clears the session
Export the wrapped handler as the val's default:
import { Hono } from "npm:hono";
import { oauthMiddleware } from "https://esm.town/v/std/oauth/middleware.ts";
const app = new Hono();
app.onError((err) => Promise.reject(err));
app.get("/", (c) => c.text("hello"));
export default oauthMiddleware(app.fetch);
You don't write the /auth/* routes yourself — the middleware adds them. Don't shadow them in your own app.
Reading the current user
Call getOAuthUserData(rawRequest) from any route. In Hono, rawRequest is c.req.raw. It returns the session data if the request is authenticated, or null otherwise.
interface SessionData {
user: {
id: string;
username: string | null;
email: string | null;
bio: string | null;
tier: "free" | "pro" | null;
type: "user" | "org";
url: string;
links: {
self: string;
profileImageUrl: string | null;
};
};
accessToken: string; // Val Town API token (act on behalf of the user)
refreshToken?: string;
idToken?: string;
expiresAt: number; // Unix timestamp (ms)
isOrgMember?: boolean; // true if user belongs to this val's org
}
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.
- 2d ago First seen · 109 lines · 83 tokens per session scan A 9fd4aa50769b
oauth is a skill published in the GitHub repository val-town/plugins (10 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 1,035 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…