product-app-api

product-app-api is a skill for Claude Code, Codex from GCWing/Sparo-OS. It costs 65 tokens per session (1,693 once invoked), scanned A, original, MIT.

A reference for building and debugging Sparo OS Product Apps, including their browser interface, optional worker process, source manifest, permissions, storage, and runtime APIs.

In plain words
What is it for?
It is for writing or reviewing Product App files such as `ui.js`, `worker.js`, and `source_manifest.json`, and for working with app services, storage, files, networking, dialogs, and runtime events.
Why use it?
It explains which APIs are available in each part of an app and how the app’s source and entry points must be configured.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for writing or reviewing Product App files such as ui.js, worker.js, and source_manifest.json, and for working with app services, storage, files, networking, dialogs, and runtime events.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gcwing/sparo-os/product-app-api
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.

Any agent
npx skills add GCWing/Sparo-OS --skill product-app-api
Clone the repo
git clone --depth 1 https://github.com/GCWing/Sparo-OS

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for product-app-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/gcwing/sparo-os/product-app-api/github.svg)](https://agentmods.dev/skills/gcwing/sparo-os/product-app-api)
Your own site
<a href="https://agentmods.dev/skills/gcwing/sparo-os/product-app-api"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/product-app-api/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.

agentmods 80×15 button for product-app-api

Your own site · 80×15
<a href="https://agentmods.dev/skills/gcwing/sparo-os/product-app-api"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/product-app-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,693 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00065 $0.01693
Opus 5.5 $0.00026 $0.00677
Sonnet 5.5 $0.00013 $0.00339
Haiku 4.5 $0.00006 $0.00169

Measured 1mo ago against content hash b669a5aeede8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

product-app-api scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `app.net.fetch(url, opts)`
bundles/skill-suites/product-app-development/skills/product-app-api/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product App API Skill

Use this skill for Product App runtime code and platform capability work. Prefer current tool output, scaffold files, and package validation results over memory.

Runtime Model

  • ui.js runs in the iframe/browser environment. It uses the DOM, standard browser APIs, ESM imports, and window.app.
  • worker.js is optional backend logic running in a separate JavaScript Worker host. Custom app.call(method, params) calls only methods exported by worker.js.
  • source_manifest.json describes entrypoints: uiEntry, optional workerEntry, styleEntries, and buildMode. Current built-in apps use nativeEsm.
  • esm_dependencies.json is the browser import-map dependency array, not an object. Write [] when there are no dependencies.
  • Extra source files are read from source/. Do not handwrite private_surface_sources; edit package source files.
  • A Product App surface implementationRef must be app://<app-id>@<version>/surfaces/<surface-id>. Do not fall back to old bundle://surface-components/... refs.

window.app Capabilities

The runtime adapter exposes window.app. A common alias is:

const runtime = () => window.app || {};

Basic properties:

  • app.appId
  • app.appDataDir
  • app.workspaceDir
  • app.theme
  • app.locale
  • app.platform
  • app.mode

Host capabilities:

  • app.fs.readFile/writeFile/readdir/stat/mkdir/rm/copyFile/rename/appendFile
  • app.shell.exec(command, opts)
  • app.net.fetch(url, opts)
  • app.os.info()
  • app.storage.get(key) / app.storage.set(key, value)
  • app.dialog.open/save/message
  • app.clipboard.writeText/readText
  • app.ai.complete/chat/cancel/getModels
  • app.backend.call/cancel/status/cancelRun/cancelStaleRuns/turnText/onEvent/offEvent
  • app.host.fillChatInput(text)
  • app.deck.renderPage(opts)
  • app.log.debug/info/warn/error
  • app.onActivate/onDeactivate/onThemeChange/onLocaleChange
  • app.i18n.t(key, params, fallback), app.i18n.setMessages(messages), app.i18n.onChange(fn)
  • app.t(localeTable, fallback): selects text from { "zh-CN": "...", "en-US": "..." } using the current locale.
  • app.on(event, fn) / app.off(event, fn): subscribes to runtime events, worker:*, backend:event, and similar events.
  • app.ui: runtime UI Kit. UI details belong in product-app-ui-polish.

Read the full file on GitHub · 157 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. 1mo ago First seen · 157 lines · 65 tokens per session scan A b669a5aeede8

Subscribe to this mod's changes

product-app-api is a skill published in the GitHub repository GCWing/Sparo-OS (25 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 1,693 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

kapso-whatsapp

How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…

desplega-ai/agent-swarm · 156 tokens

apps

Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.

desplega-ai/agent-swarm · 43 tokens

swarm-scripts

Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, files and bash over the agent-fs drive (ctx.fs…

desplega-ai/agent-swarm · 100 tokens

composio

Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…

desplega-ai/agent-swarm · 128 tokens

motion-design-video-analysis

Reverse-engineer a short motion-design / product-update video (animation technique, timing and easing, composition, transitions, likely tooling, vibe, audio) and produce a rebuild spec someone can build from. Default path is one call to google/gemini-3.8-flash over sampled frames, then a mandatory by-eye check of…

desplega-ai/agent-swarm · 107 tokens

open-prompt-showreel

Make a design-led motion-graphics video (showreel, eval comparison, feature or bug-hunt story) from one open prompt. Claude Opus at max effort designs, codes and renders the whole thing itself in a scratch dir, with no template and no repo PR. Use for any "make a video for X" / "do a showreel for Y" / "a little…

desplega-ai/agent-swarm · 181 tokens