Knowledge Work Plugins is an open-source collection of Claude extensions organized around roles such as productivity, sales, and customer support. Each plugin combines role-specific guidance, connectors, commands, and sub-agents so knowledge workers can use Claude with their team’s tools and processes. The catalogue entries are examples of, or workflows from, this plugin collection.
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/anthropics/knowledge-work-plugins/meeting-sdknpx skills add anthropics/knowledge-work-plugins --skill meeting-sdkgit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWrote 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/anthropics/knowledge-work-plugins/meeting-sdk)<a href="https://agentmods.dev/skills/anthropics/knowledge-work-plugins/meeting-sdk"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/meeting-sdk.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.02877 |
| Opus 5 | $0.00025 | $0.01438 |
| Sonnet 5 | $0.00010 | $0.00575 |
| Haiku 4.5 | $0.00005 | $0.00288 |
Grade A, and why
build-zoom-meeting-sdk-app 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- build-zoom-meeting-sdk-app — 95% identical, 18 lines differ
- zoom-meeting-sdk — 94% identical, 61 lines differ
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-zoom-meeting-sdk-app
Background reference for embedded Zoom meetings across web, mobile, desktop, and Linux bot environments. Prefer build-zoom-meeting-app or build-zoom-bot first, then route here for platform detail.
Zoom Meeting SDK
Embed the full Zoom meeting experience into web, mobile, desktop, and headless integrations.
Hard Routing Guardrail (Read First)
- If the user asks to embed/join meetings inside their app UI, route to Meeting SDK implementation.
- Do not switch to REST-only meeting link flow unless the user explicitly asks for meeting resource management or browser
join_urllinks. - Meeting SDK join path requires SDK signature + SDK join call; REST
join_urlis not a Meeting SDK join payload.
Prerequisites
- Zoom app with Meeting SDK credentials
- SDK Key and Secret from Marketplace
- Platform-specific development environment (Web, Android, iOS, macOS, Unreal, Electron, Linux, or Windows)
Need help with OAuth or signatures? See the zoom-oauth skill for authentication flows.
Need pre-join diagnostics on web? Use probe-sdk before Meeting SDK init/join to gate low-readiness devices/networks.
Start troubleshooting fast: Use the 5-Minute Runbook before deep debugging.
Quick Start (Web - Client View via CDN)
<script src="https://source.zoom.us/3.1.6/lib/vendor/react.min.js"></script>
<script src="https://source.zoom.us/3.1.6/lib/vendor/react-dom.min.js"></script>
<script src="https://source.zoom.us/3.1.6/lib/vendor/redux.min.js"></script>
<script src="https://source.zoom.us/3.1.6/lib/vendor/redux-thunk.min.js"></script>
<script src="https://source.zoom.us/3.1.6/lib/vendor/lodash.min.js"></script>
<script src="https://source.zoom.us/3.1.6/zoom-meeting-3.1.6.min.js"></script>
<script>
// CDN provides ZoomMtg (Client View - full page)
// For ZoomMtgEmbedded (Component View), use npm instead
ZoomMtg.preLoadWasm();
ZoomMtg.prepareWebSDK();
ZoomMtg.init({
leaveUrl: window.location.href,
patchJsMedia: true,
disableCORP: !window.crossOriginIsolated,
success: function() {
ZoomMtg.join({
sdkKey: 'YOUR_SDK_KEY',
signature: 'YOUR_SIGNATURE', // Generate server-side!
meetingNumber: 'MEETING_NUMBER',
userName: 'User Name',
passWord: '', // Note: camelCase with capital W
success: function(res) { console.log('Joined'); },
error: function(err) { console.error(err); }
});
},
error: function(err) { console.error(err); }
});
</script>
What ships with it
60 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.
- android/android.md 856 B
- android/concepts/architecture.md 781 B
- android/concepts/lifecycle-workflow.md 724 B
- android/examples/join-start-pattern.md 709 B
- android/references/android-reference-map.md 834 B
- android/references/environment-variables.md 833 B
- android/references/versioning-and-compatibility.md 666 B
- android/RUNBOOK.md 2.3 KB
- android/scenarios/high-level-scenarios.md 663 B
- android/SKILL.md 1.8 KB
- android/troubleshooting/common-issues.md 823 B
- electron/concepts/high-level-scenarios.md 818 B
- electron/concepts/lifecycle-workflow.md 937 B
- electron/concepts/sdk-architecture-pattern.md 726 B
- electron/examples/authentication-pattern.md 485 B
- electron/examples/join-meeting-pattern.md 509 B
- electron/examples/raw-data-pattern.md 561 B
- electron/examples/setup-guide.md 771 B
- electron/references/electron-reference.md 541 B
- electron/references/module-map.md 765 B
- electron/RUNBOOK.md 2.3 KB
- electron/SKILL.md 2.9 KB
- electron/troubleshooting/common-issues.md 823 B
- electron/troubleshooting/deprecated-and-contradictions.md 1.2 KB
- electron/troubleshooting/version-drift.md 467 B
- ios/concepts/architecture.md 660 B
- ios/concepts/lifecycle-workflow.md 591 B
- ios/examples/join-start-pattern.md 610 B
- ios/ios.md 737 B
- ios/references/environment-variables.md 813 B
- ios/references/ios-reference-map.md 712 B
- ios/references/versioning-and-compatibility.md 597 B
- ios/RUNBOOK.md 2.3 KB
- ios/scenarios/high-level-scenarios.md 655 B
- ios/SKILL.md 1.4 KB
- ios/troubleshooting/common-issues.md 661 B
- linux/concepts/high-level-scenarios.md 15 KB
- linux/linux.md 11 KB
- linux/meeting-sdk-bot.md 30 KB
- linux/references/linux-reference.md 21 KB
- linux/RUNBOOK.md 2.3 KB
- linux/SKILL.md 15 KB
- macos/concepts/architecture.md 719 B
- macos/concepts/lifecycle-workflow.md 489 B
- macos/examples/join-start-pattern.md 584 B
- macos/macos.md 708 B
- macos/references/environment-variables.md 827 B
- macos/references/macos-reference-map.md 790 B
- macos/references/versioning-and-compatibility.md 710 B
- macos/RUNBOOK.md 2.3 KB
- macos/scenarios/high-level-scenarios.md 624 B
- macos/SKILL.md 1.4 KB
- macos/troubleshooting/common-issues.md 726 B
- react-native/concepts/architecture.md 581 B
- react-native/concepts/auth-and-token-model.md 514 B
- react-native/concepts/high-level-scenarios.md 932 B
- react-native/concepts/lifecycle-workflow.md 615 B
- react-native/examples/join-meeting-pattern.md 415 B
- react-native/examples/provider-hook-pattern.md 332 B
- react-native/examples/setup-guide.md 1.1 KB
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 First seen · 256 lines · 50 tokens per session scan A 85d99b894bf6
build-zoom-meeting-sdk-app is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,849 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 2,877 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.