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/zoom/zoom-plugin/startnpx skills add zoom/zoom-plugin --skill startgit clone --depth 1 https://github.com/zoom/zoom-pluginWhat 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 | $0.00043 | $0.00609 |
| Opus 5 | $0.00022 | $0.00304 |
| Sonnet 5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
start 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start
Use this as the default entry skill for the plugin.
What This Skill Does
- Classifies the request by job-to-be-done, not by product name alone
- Routes into the right implementation skill
- Pulls in product-specific Zoom references only after the route is clear
- Prevents common early mistakes, especially Meeting SDK vs Video SDK and REST API vs MCP confusion
Routing Table
| If the user wants to... | Route to |
|---|---|
| Choose the right Zoom surface for a new project | plan-zoom-product |
| Create, select, or validate a Zoom Marketplace app or manifest | setup-zoom-marketplace-app |
| Set up OAuth, tokens, scopes, or app credentials | setup-zoom-oauth |
| Embed or customize a Zoom meeting flow | build-zoom-meeting-app |
| Build a bot, recorder, or real-time meeting processor | build-zoom-bot |
| Use Zoom-hosted MCP for AI workflows | setup-zoom-mcp |
| Debug a broken integration | debug-zoom |
Supporting Zoom References
Use these only after selecting the workflow:
- general
- rest-api
- meeting-sdk
- video-sdk
- webhooks
- websockets
- oauth
- Marketplace app management
- zoom-mcp
Operating Rules
- Prefer one clear recommendation over a product catalog dump.
- Ask a short clarifier only when the route is genuinely ambiguous.
- Keep the first response architectural and actionable, then go deep.
- Pull in deeper references only when they directly help the current decision or implementation.
- When a requested integration needs a Marketplace app created, updated, or validated, chain through setup-zoom-marketplace-app before OAuth or product implementation, then resume the originating workflow.
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 · 52 lines · 43 tokens per session scan A 244aecb84839
start is a skill published in the GitHub repository zoom/zoom-plugin (7 stars, last pushed 25d ago), licensed MIT. It adds 43 tokens to every session and 609 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…