plugin-host

plugin-host is a skill for Claude Code from Josh-E-S/awesome-pexip-skills. It costs 110 tokens per session (3,388 once invoked), scanned A, original, MIT.

Instructions for building the host side of Pexip's plugin system. Plugins run in isolated browser frames and communicate with the main meeting app through message-based requests.

In plain words
What is it for?
Loading plugin manifests, isolating plugin frames, handling communication, adding buttons and panels, showing forms or notifications, and routing meeting actions.
Why use it?
The host must safely load plugins, verify their messages, and connect their controls to meeting features.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pexip plugin — 17 skills shipped together

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.

agentmods
npx agentmods add skills/josh-e-s/awesome-pexip-skills/plugin-host
Any agent
npx skills add Josh-E-S/awesome-pexip-skills --skill plugin-host
Clone the repo
git clone --depth 1 https://github.com/Josh-E-S/awesome-pexip-skills

Made for: Claude Code.

Or install pexip, the plugin that ships this one along with the rest of its 17 skills.

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 plugin-host

README.md
[![agentmods](https://agentmods.dev/badge/skills/josh-e-s/awesome-pexip-skills/plugin-host.svg)](https://agentmods.dev/skills/josh-e-s/awesome-pexip-skills/plugin-host)
Your own site
<a href="https://agentmods.dev/skills/josh-e-s/awesome-pexip-skills/plugin-host"><img src="https://agentmods.dev/badge/skills/josh-e-s/awesome-pexip-skills/plugin-host.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00110 $0.03388
Opus 5 $0.00055 $0.01694
Sonnet 5 $0.00022 $0.00678
Haiku 4.5 $0.00011 $0.00339

Measured 6d ago against content hash a2431096e6e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

plugin-host 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 6d 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.

skills/plugin-host/SKILL.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pexip plugin host

Pexip plugins are sandboxed iframes that drive the host app via postMessage RPC. The plugin can:

  • Add toolbar buttons / participant menu items / settings menu items
  • Open panel widgets (visible iframes inside the meeting UI)
  • Show modal forms / prompts / toasts
  • Call most of the conference SDK (mute, kick, setLayout, breakout, sendMessage, etc.)
  • Subscribe to events (participant joins, conference status, language change, transfer events)

Webapp3's PluginManager is the host implementation. ~1,000 LOC across src/plugins/ plus the @pexip/plugin-api SDK. This skill captures the architecture; if you need to write plugins (the iframe side), see Pexip's separate plugin developer portal.

The architecture in one diagram

manifest.json declares plugins[]
        ↓
<PluginManager> renders one hidden <iframe sandbox> per plugin
        ↓
plugin loads, calls registerPlugin() which sends "syn" RPC via postMessage
        ↓
host validates: is the message source one of our iframes?
        ↓
host creates Channel, sends "ack" reply, syncs initial state to plugin
        ↓
plugin issues UI/conference RPCs (button:add, widget:add, conference:mute, etc.)
        ↓
host updates React state for UI ops, calls infinity SDK for conference ops
        ↓
host subscribes to all infinity signals → forwards to plugins as events

Manifest entry

{
    "plugins": [
        {
            "src": "./plugins/my-plugin/index.html",
            "id": "my-plugin",
            "sandboxValues": ["allow-scripts", "allow-same-origin"]
        }
    ]
}

Webapp3 renders this as:

<iframe
    id={plugin.id}
    sandbox={getValidSandboxValues(plugin)}
    src={plugin.src}
    aria-hidden
    className="b-zero"  // 0×0, invisible
/>

Plugins are logical, not visible — they're invisible iframes that issue commands. To show UI, plugins request a widget (a separate visible iframe) or call ui:button:add / ui:form:open / etc. (rendered natively by the host).

Read the full file on GitHub · 355 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. 6d ago First seen · 355 lines · 110 tokens per session scan A a2431096e6e2

Subscribe to this mod's changes

plugin-host is a skill published in the GitHub repository Josh-E-S/awesome-pexip-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 3,388 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens