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 cobrowse-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/cobrowse-sdk)<a href="https://agentmods.dev/skills/anthropics/knowledge-work-plugins/cobrowse-sdk"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/cobrowse-sdk/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.
<a href="https://agentmods.dev/skills/anthropics/knowledge-work-plugins/cobrowse-sdk"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/cobrowse-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 173 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 174 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 270 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 309 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00045 | $0.08135 |
| Opus 5.5 | $0.00018 | $0.03254 |
| Sonnet 5.5 | $0.00009 | $0.01627 |
| Haiku 4.5 | $0.00005 | $0.00813 |
Grade B, and why
zoom-cobrowse-sdk scanned grade B 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const response = await fetch("https://YOUR_TOKEN_SERVICE_BASE_URL", { method: "POST", Copies of this mod
2 near-identical copies found in the catalogue:
- zoom-cobrowse-sdk — 100% identical, 5 lines differ
- zoom-cobrowse-sdk — 98% identical, 18 lines differ
How it starts
The opening of the file, as written. The whole thing — 895 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zoom Cobrowse SDK - Web Development
Background reference for collaborative browsing on the web with Zoom Cobrowse SDK. Use this after the support workflow is clear and you need implementation detail.
Official Documentation: https://developers.zoom.us/docs/cobrowse-sdk/
API Reference: https://marketplacefront.zoom.us/sdk/cobrowse/
Quickstart Repository: https://github.com/zoom/CobrowseSDK-Quickstart
Auth Endpoint Sample: https://github.com/zoom/cobrowsesdk-auth-endpoint-sample
Quick Links
New to Cobrowse SDK? Follow this path:
- Get Started Guide - Complete setup from credentials to first session
- Session Lifecycle - Understanding customer and agent flows
- JWT Authentication - Token generation and security
- Customer Integration - Integrate SDK into your website
- Agent Integration - Set up agent portal (iframe or npm)
Core Concepts:
- Two Roles Pattern - Customer vs Agent architecture
- Session Lifecycle - PIN generation, connection, reconnection
- JWT Authentication - SDK Key vs API Key, role_type, claims
- Distribution Methods - CDN vs npm (BYOP)
Features:
- Annotation Tools - Drawing, highlighting, pointer tools
- Privacy Masking - Hide sensitive fields from agents
- Remote Assist - Agent can scroll customer's page
- Multi-Tab Persistence - Session continues across tabs
- BYOP Mode - Bring Your Own PIN with npm integration
Troubleshooting:
- Common Issues - Quick diagnostics and solutions
- Error Codes - Complete error reference
- CORS and CSP - Cross-origin and security policy configuration
- Browser Compatibility - Supported browsers and limitations
- 5-Minute Runbook - Fast preflight checks before deep debugging
What ships with it
32 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.
- concepts/distribution-methods.md 348 B
- concepts/jwt-authentication.md 362 B
- concepts/session-lifecycle.md 360 B
- concepts/two-roles-pattern.md 1.4 KB
- examples/agent-integration.md 217 B
- examples/annotations.md 224 B
- examples/auto-reconnection.md 213 B
- examples/byop-custom-pin.md 223 B
- examples/customer-integration.md 222 B
- examples/multi-tab-persistence.md 228 B
- examples/privacy-masking.md 218 B
- examples/remote-assist.md 231 B
- examples/session-events.md 220 B
- get-started.md 15 KB
- references/api-official.md 1.6 KB
- references/api-reference.md 117 B
- references/api.md 74 B
- references/authorization-official.md 2.0 KB
- references/authorization.md 104 B
- references/environment-variables.md 778 B
- references/error-codes.md 190 B
- references/features-official.md 1.9 KB
- references/features.md 89 B
- references/get-started-official.md 2.0 KB
- references/get-started.md 98 B
- references/session-events.md 150 B
- references/settings-reference.md 193 B
- RUNBOOK.md 2.7 KB
- troubleshooting/browser-compatibility.md 227 B
- troubleshooting/common-issues.md 2.5 KB
- troubleshooting/cors-csp.md 283 B
- troubleshooting/error-codes.md 216 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.
- 1mo ago First seen · 895 lines · 45 tokens per session scan B abb461e07f15
zoom-cobrowse-sdk is a skill published in the GitHub repository anthropics/knowledge-work-plugins (30,501 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 8,135 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.