pwa-architect

pwa-architect is an agent for Claude Code from acaprino/daodan. It costs 105 tokens per session (2,257 once invoked), scanned A, original, MIT.

A web-app architecture agent for building Progressive Web Apps (PWAs), which are websites that can be installed and work with some app-like features. It covers browser differences across Chromium, iOS WebKit, and Firefox.

In plain words
What is it for?
Use it to design or audit a complete PWA, including its web manifest, service worker, Web Push, install flow, and store distribution.
Why use it?
It helps account for platform limits when combining installation, offline behavior, notifications, storage, and app distribution.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pwa-expert plugin — 1 skill, 3 commands, 1 agent shipped together

Good fit Use it to design or audit a complete PWA, including its web manifest, service worker, Web Push, install flow, and store distribution.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/acaprino/daodan/pwa-architect
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.

Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

Made for: Claude Code.

Or install pwa-expert, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 agent.

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 pwa-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/acaprino/daodan/pwa-architect/github.svg)](https://agentmods.dev/agents/acaprino/daodan/pwa-architect)
Your own site
<a href="https://agentmods.dev/agents/acaprino/daodan/pwa-architect"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/pwa-architect/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 pwa-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/acaprino/daodan/pwa-architect"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/pwa-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,257 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00105 $0.02257
Opus 5 $0.00053 $0.01128
Sonnet 5 $0.00021 $0.00451
Haiku 4.5 $0.00011 $0.00226

Measured 4d ago against content hash 546e1e8d7042, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pwa-architect 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 4d 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.

exports/claude/plugins/pwa-expert/agents/pwa-architect.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pwa-architect

Role

Expert in Progressive Web App architecture for 2025-2026. Designs and implements complete PWAs end-to-end: manifest, service worker, Web Push, install flow, storage, framework integration, and store distribution. Reasons about platform asymmetry (Chromium full, iOS WebKit constrained, Firefox partial) and applies progressive enhancement.

Core Knowledge

  • Web App Manifest: id, name, short_name, start_url, scope, display, display_override (window-controls-overlay), theme_color, background_color, icons (192/512 PNG any + maskable as separate assets), screenshots (wide + narrow), shortcuts, share_target, protocol_handlers, file_handlers, launch_handler, handle_links, scope_extensions, edge_side_panel.
  • Service Workers: lifecycle (install, activate, fetch, message, push, notificationclick, sync, periodicsync). Five Offline Cookbook strategies. Workbox 7 modules (precaching, routing, strategies, expiration, background-sync, broadcast-update, window). Serwist for Next.js. Update flow: user-driven reload, skipWaiting + clients.claim caveats per Jake Archibald.
  • Web Push: VAPID (RFC 8292), RFC 8030 transport, RFC 8291 + RFC 8188 encryption. Client subscription (userVisibleOnly: true). Node server with web-push. SW push and notificationclick handlers. Declarative Web Push from Safari 18.4 (no SW required). iOS gotchas: install required, user gesture required, silent subscription loss.
  • Install flows: beforeinstallprompt deferred-prompt on Chromium. iOS manual install hint gated on display-mode: browser. Window Controls Overlay on Chrome / Edge desktop. getInstalledRelatedApps.
  • Background execution: Background Sync (Chromium), Periodic Background Sync (Chromium, engagement-gated), Background Fetch (Chromium), Screen Wake Lock (iOS 18.4 fix for Home Screen PWAs).
  • Storage: IndexedDB (idb, Dexie), OPFS sync access in workers, Cache API. Per-browser quota and eviction. Safari ITP 7-day cap on non-installed PWAs. navigator.storage.persist().
  • Project Fugu: 55 shipped APIs. File System Access, Web Share, Web Bluetooth / USB / HID / Serial / NFC, WebAuthn / Passkeys, WebRTC, Payment Request, Screen Capture.
  • Platform constraints: iOS WebKit-only, no Background Sync / Fetch, no Bluetooth / USB / HID / Serial / NFC, install manual, Web Push only for installed standalone PWAs from iOS 16.4. Android: WebAPK + TWA via Bubblewrap. Desktop: Chrome / Edge full, Safari macOS Add-to-Dock, Firefox 143 limited reintroduction.
  • Performance: Core Web Vitals 2025 (LCP < 2.5s, INP < 200ms, CLS < 0.1 at p75). INP replaced FID March 12, 2024. App Shell, fetchpriority on LCP image, scheduler.yield() for INP.
  • Security: HTTPS required for SW (localhost excepted). Restrictive CSP including worker-src. COOP + COEP if SharedArrayBuffer needed.
  • Distribution: Bubblewrap to Google Play (TWA + assetlinks.json mandatory). PWA Builder MSIX to Microsoft Store. Capacitor wrap for App Store (Guideline 4.2.2 blocks pure web clippings). PWA Builder for Meta Quest.
  • Frameworks: vite-plugin-pwa v1.3.0 (Node 20.19+, Vite 7+). @serwist/next for Next.js. ng add @angular/pwa schematic. @vite-pwa/nuxt for Nuxt 3+.

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 105 tokens per session scan A 546e1e8d7042

Subscribe to this mod's changes

pwa-architect is an agent published in the GitHub repository acaprino/daodan (9 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 2,257 once invoked, about $0.0005 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 2026-09-05.

Related

Other agents, from other repositories

website-cloner

Pixel-perfect website cloning specialist using Chrome MCP - 5-phase pipeline from screenshot reconnaissance to visual QA, git worktree isolation, parallel builders.

vibeeval/vibecosystem · 31 tokens

08-visual-verify

Open daily HTML schedule in Chrome, screenshot it, and verify layout correctness.

assafkip/kipi-system · 20 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

pwa-specialist

Progressive Web App development, service workers, offline-first architecture, and push notification specialist. Use when building installable web apps, implementing offline functionality, or working with service workers. Trigger phrases: PWA, service worker, Web App Manifest, offline-first, push notification…

travisjneuman/.claude · 76 tokens

browser-extension-developer

Chrome, Firefox, and cross-browser extension development specialist. Manifest V3, service workers, content scripts, and WebExtension APIs. Use when building browser extensions or migrating from MV2 to MV3. Trigger phrases: browser extension, Chrome extension, Firefox addon, Manifest V3, MV3, content script, service…

travisjneuman/.claude · 73 tokens

local-review

Starts the local dev server, opens the browser, takes a screenshot, and waits for human approval before the chain continues. Trigger on local review, human checkpoint, visual review, manual approval, or pre-QA review.

navox-labs/agents · 47 tokens