stoop-platform

A reference for the Stoop platform's software development kit, which lets a website use shared data, user identity, AI, files, messaging channels, and a house-style theme. The SDK is a set of ready-made programming interfaces.

In plain words
What is it for?
Use it before writing code that calls Stoop's database, identity, AI, file, channel, or theme features.
Why use it?
It gives developers the platform-specific rules and examples needed to build a Stoop site that works with the platform at runtime.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/mislavjc/stoop/stoop-platform
Any agent
npx skills add mislavjc/stoop --skill stoop-platform
Clone the repo
git clone --depth 1 https://github.com/mislavjc/stoop

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.02362
Opus 5 $0.00028 $0.01181
Sonnet 5 $0.00011 $0.00472
Haiku 4.5 $0.00006 $0.00236

Measured 2d ago against content hash ff66e808b60f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stoop-platform 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.

skills/stoop-platform/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The stoop platform SDK

What a stoop site can do at runtime without any backend code of its own. This is the same surface however the site was published — from a folder with the stoop CLI, or over HTTP with an API key.

Loading it

Every page that needs data or identity loads the SDK. It is served by the platform on the site's own origin — do not bundle, vendor, or CDN it:

<script src="/__platform/sdk.js"></script>

It installs window.platform.

Database — platform.db.collection(name)

Schemaless JSON documents, shared by all visitors of the site, with realtime updates:

const votes = platform.db.collection("votes");
await votes.create({ spot: "Taco Cart" }); // → doc; the server assigns doc.id
await votes.list();                        // → doc[] (newest first)
await votes.get(id);                       // → doc
await votes.update(id, { count: 2 });      // → doc (shallow merge)
await votes.delete(id);                    // → null
const stop = votes.subscribe({             // realtime; returns unsubscribe fn
  onCreate: (doc) => {},
  onUpdate: (doc) => {},
  onDelete: (id) => {},
});

// Queries: equality filters, one sort field (- prefix = descending;
// _created / _updated sort by timestamp), and a page-size limit.
await votes.list({ where: { spot: "Taco Cart" }, sort: "-_created", limit: 50 });
// Pagination for big collections: cursor is null on the last page.
const { docs, cursor } = await votes.page({ limit: 100 });
const rest = await votes.page({ limit: 100, cursor });

// Access rules — make a collection read-only or invisible to visitors.
// Only site members may call this ("public"/"public" is the default).
await votes.setRules({ read: "public", write: "members" });
  • Subscribe events fire for every client's writes, including this page's own: render from list() + subscribe events and don't also apply local writes to the UI, or they will show up twice.
  • list() returns newest first — reverse it when appending rows in chronological order, so live onCreate appends continue the same order.
  • list() returns at most one page (1000 docs); use page() and follow cursor when a collection can grow past that.
  • where is exact equality on top-level fields only (no ranges, no substring match) — filter client-side for anything richer.
  • No transactions or atomic increments: concurrent update()s to the same key are last-write-wins, so a shared counter can drop clicks. When every event must count (votes, tallies), create() one document per event and count them client-side.
  • Documents may carry a platform-stamped _by author ({ id, name }). Client-sent values are ignored, and anonymous visitors cannot edit or delete documents authored by someone else.
  • setRules({ read, write }) with "public" | "members" persists per collection. Use write: "members" for owner-curated content (menus, announcements) that visitors read but must not change; visitor sites calling it get a 403, so gate it on user action, not page load.

Read the full file on GitHub · 230 lines

Changes

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.

  1. 2d ago First seen · 230 lines · 56 tokens per session scan A ff66e808b60f

Subscribe to this mod's changes

stoop-platform is a skill published in the GitHub repository mislavjc/stoop (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,362 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.

Related

Other skills, from other repositories

github-issue-workflow

How to start work on a GitHub issue in the munkel repo — check for an existing draft PR and the issue's assignee first to avoid duplicating work someone already owns, claim the issue by assigning it, then open a draft PR linked with "Closes.

limehq/munkel · 60 tokens

munkel

Send ephemeral end-to-end-encrypted messages that appear in friends' MacBook notches, via the munkel CLI (macOS). Use when the user wants to message, ping, or notify someone in a Munkel channel, broadcast to a channel, or list Munkel channels and members.

limehq/munkel · 65 tokens

sharehtml-collaboration

Use when a user wants to deploy, update, diff, pull, or review feedback on documents managed with the sharehtml CLI. This skill covers safe deploy workflows, reviewing unresolved comments, finding documents by name with sharehtml list, and presenting diffs in human language before overwriting. Keep documents private…

jonesphillip/sharehtml · 81 tokens

frontend-design-landing-page

Marketing landing page and conversion-focused product page reference. Use this skill when building hero sections, feature grids, pricing pages, testimonials, CTAs, footers, navigation bars, or any public-facing marketing surface. Covers a warm, professional, developer-friendly design language (cream backgrounds…

cloudflare/vibesdk · 106 tokens

frontend-design-saas

S-tier SaaS dashboard and product UI reference. Use this skill when building application shells, data tables, settings panels, billing pages, dashboards, auth flows, admin tools, or any internal/customer-facing SaaS product UI. Inspired by Stripe, Linear, Vercel, Airbnb, Notion. Covers neutral-led design tokens…

cloudflare/vibesdk · 105 tokens

cloudflare-bundler-apps

Author Cloudflare Worker Bundler-compatible apps that build and preview correctly inside a space. Use this skill whenever you scaffold, modify, or deploy a project that will be built with @cloudflare/worker-bundler (i.e. anything served from /space/:name/preview/:branch/). Covers wrangler config, project layout…

cloudflare/vibesdk · 105 tokens