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 skills add anthropics/knowledge-work-plugins --skill virtual-agentgit 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/virtual-agent)<a href="https://agentmods.dev/skills/anthropics/knowledge-work-plugins/virtual-agent"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/virtual-agent.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 5.1 | $0.00044 | $0.00812 |
| Opus 5 | $0.00022 | $0.00406 |
| Sonnet 5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
build-zoom-virtual-agent 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- build-zoom-virtual-agent — 94% identical, 1 lines differ
- virtual-agent — 88% identical, 13 lines differ
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-zoom-virtual-agent
Background reference for Zoom Virtual Agent across:
- Web campaign/chat embeds.
- Android WebView wrappers.
- iOS WKWebView wrappers.
- Knowledge-base sync and custom API ingestion.
Official docs:
- https://developers.zoom.us/docs/virtual-agent/
- https://developers.zoom.us/docs/virtual-agent/web/
- https://developers.zoom.us/docs/virtual-agent/android/
- https://developers.zoom.us/docs/virtual-agent/ios/
Routing Guardrail
- If the user is implementing Contact Center app surfaces inside Zoom client, chain with ../contact-center/SKILL.md.
- If the user needs backend knowledge-base CRUD or automation scripts, chain with ../rest-api/SKILL.md and ../oauth/SKILL.md.
- If the user asks only for website bot embed and campaign controls, stay on web/SKILL.md.
- If the user asks for mobile native wrappers around web chat, route to android/SKILL.md or ios/SKILL.md.
Quick Links
- concepts/architecture-and-lifecycle.md
- scenarios/high-level-scenarios.md
- references/versioning-and-drift.md
- references/samples-validation.md
- references/environment-variables.md
- troubleshooting/common-drift-and-breaks.md
- RUNBOOK.md
Platform skills:
Common Lifecycle Pattern
- Configure campaign or entry ID in Virtual Agent admin.
- Initialize SDK in web or WebView container.
- Wait for readiness (
zoomCampaignSdk:readyorwaitForReady()) before calling APIs. - Register bridge handlers (
exitHandler,commonHandler,support_handoff) when native orchestration is needed. - Handle conversation lifecycle (
engagement_started,engagement_ended) and UI state. - End chat (
endChat) and clean up listeners.
What ships with it
22 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/concepts/webview-lifecycle.md 389 B
- android/examples/js-bridge-patterns.md 1023 B
- android/references/android-reference-map.md 640 B
- android/SKILL.md 1.5 KB
- android/troubleshooting/common-issues.md 650 B
- concepts/architecture-and-lifecycle.md 949 B
- ios/concepts/webview-lifecycle.md 451 B
- ios/examples/js-bridge-patterns.md 936 B
- ios/references/ios-reference-map.md 641 B
- ios/SKILL.md 1.4 KB
- ios/troubleshooting/common-issues.md 583 B
- references/environment-variables.md 844 B
- references/samples-validation.md 1.0 KB
- references/versioning-and-drift.md 823 B
- RUNBOOK.md 1.0 KB
- scenarios/high-level-scenarios.md 961 B
- troubleshooting/common-drift-and-breaks.md 942 B
- web/concepts/lifecycle-and-events.md 608 B
- web/examples/campaign-and-entry-patterns.md 944 B
- web/references/web-reference-map.md 590 B
- web/SKILL.md 1.5 KB
- web/troubleshooting/common-issues.md 669 B
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 · 74 lines · 44 tokens per session scan A 5f41eeb6b6ec
build-zoom-virtual-agent is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,902 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 812 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…