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/gettalon/talon-plugins/hub-setupnpx skills add gettalon/talon-plugins --skill hub-setupgit clone --depth 1 https://github.com/gettalon/talon-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/gettalon/talon-plugins/hub-setup)<a href="https://agentmods.dev/skills/gettalon/talon-plugins/hub-setup"><img src="https://agentmods.dev/badge/skills/gettalon/talon-plugins/hub-setup.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 | $0.00038 | $0.02450 |
| Opus 5 | $0.00019 | $0.01225 |
| Sonnet 5 | $0.00008 | $0.00490 |
| Haiku 4.5 | $0.00004 | $0.00245 |
Grade A, and why
hub-setup 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 3d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channel Adapter Setup Guide
Help the user choose and configure which channel adapter to use with the Talon Hub plugin. There are 22 options: the default WebSocket server plus 21 platform-specific adapters.
Development Mode
During the research preview, hub requires the official allowlist. To use talon-hub:
claude --dangerously-load-development-channels plugin:hub@gettalon-talon-plugins
The plugin: prefix tells Claude Code to load this hub plugin and bypass the allowlist check.
Settings: ~/.talon/settings.json
The hub reads all configuration from ~/.talon/settings.json. Create it if it doesn't exist.
Full schema
{
"servers": [
{
"url": "ws://localhost:9090",
"port": 9090
}
],
"connections": [
{
"url": "unix:///tmp/talon-9090.sock",
"name": "remote-hub",
"transport": "unix"
}
],
"transports": {
"telegram": { "botToken": "YOUR_BOT_TOKEN" },
"discord": { "botToken": "YOUR_DISCORD_TOKEN" },
"slack": { "botToken": "xoxb-...", "appToken": "xapp-..." },
"websocket": {}
},
"access": {
"requireApproval": true,
"forceApprovalAll": false,
"allowlist": ["agent-name-1", "agent-name-2"],
"denylist": ["bad-agent"]
},
"hooks": [
{ "event": "onMessage", "command": "echo 'message received'" }
],
"contacts": {
"alice": {
"name": "Alice",
"channels": [{ "type": "telegram", "id": "12345", "url": "telegram://12345" }]
},
"bob": {
"name": "Bob",
"channels": [
{ "type": "slack", "id": "U123", "url": "slack://U123" },
{ "type": "telegram", "id": "67890", "url": "telegram://67890" }
]
}
},
"state": {
"chatRoutes": {},
"groups": {},
"targets": {}
}
}
Field reference
| Field | Type | Description |
|---|---|---|
servers |
array | Hub server instances to start. Each has url and port. |
connections |
array | Remote hubs or agents to connect to on startup. url (ws://, unix://), name, optional transport and config. |
transports |
object | Channel adapter configs. Keys are channel types: telegram, websocket, discord, slack, etc. Each adapter has its own config fields. |
access |
object | Access control. requireApproval gates new agents, allowlist auto-approves named agents, denylist blocks agents. |
hooks |
array | Shell commands to run on events. { "event": "onMessage", "command": "..." } |
contacts |
object | Named contacts with many-to-many channel info. Each contact can have multiple channels. Used for edge send <name> routing. |
state |
object | Runtime state: chatRoutes, groups, targets. Managed by the hub — don't edit manually. |
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.
- 3d ago First seen · 253 lines · 38 tokens per session scan A b60af4f79279
hub-setup is a skill published in the GitHub repository gettalon/talon-plugins (6 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 2,450 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 2026-08-31.
Other skills, from other repositories
codex-browser
Control Chrome via Codex Desktop's browser bridge. 52 MCP tools for tabs, navigation, DOM, input, CDP, network, file upload, dialog handling, and diagnostics.
qa-runner
Use when asked to "run QA", "qa check", "test checklist", or execute QA checklists against a running app via browser automation. Requires the browser-bridge MCP server and Chrome extension.
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.
browse
Use when asked to interact with a web browser — navigate, click, fill forms, take screenshots, run JavaScript, or read page content. Requires the browser-bridge MCP server and Chrome extension.
NanoBanana-PPT-Skills
Skill "NanoBanana-PPT-Skills" from girish6055/NanoBanana-PPT-Skills, covering ppt generator pro - claude code skill, 📋 元数据, ✨ 功能特性, 核心功能 and 新功能 (v2.0).
codex-browser
Control Chrome or Edge via the ChatGPT desktop app's browser bridge (formerly Codex Desktop). 52 MCP tools for tabs, navigation, DOM, input, CDP, network, file upload, dialog handling, and diagnostics.