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.
/plugin marketplace add gettalon/talon-pluginsnpx agentmods add plugins/gettalon/talon-plugins/marketplacegit clone --depth 1 https://github.com/gettalon/talon-pluginsGrade A, and why
gettalon-talon-plugins 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "gettalon-talon-plugins",
"owner": {
"name": "Talon",
"email": "[email protected]"
},
"metadata": {
"description": "Official Talon plugins for Claude Code — browser control, automation, and more"
},
"plugins": [
{
"name": "talon",
"source": "./plugins/talon",
"description": "All-in-one Talon plugin — browser control, hub (22 adapters), computer use, AI dispatch, autoresearch, GitLab scrum. Use /talon:* commands.",
"version": "1.0.0",
"author": {
"name": "Talon"
},
"category": "all",
"keywords": [
"talon",
"browser",
"hub",
"computer-use",
"ai-dispatch",
"autoresearch",
"gitlab"
]
},
{
"name": "talon-web",
"source": "./plugins/browser-control",
"description": "Full browser control via Chrome DevTools Protocol. Navigate, click, fill forms, screenshot, run JS.",
"version": "1.0.0",
"author": {
"name": "Talon"
},
"category": "browser",
"keywords": [
"browser",
"chrome",
"cdp",
"automation",
"web"
]
},
{
"name": "hub",
"source": "./plugins/hub",
"description": "Universal hub — connect any client via WebSocket. Full hook event forwarding, permission relay, bidirectional chat.",
"version": "1.2.24",
"author": {
"name": "Talon"
},
"category": "hub",
"keywords": [
"hub",
"websocket",
"hooks",
"permissions",
"chat",
"relay",
"universal"
]
},
{
"name": "talon-computer-use",
"source": "./plugins/computer-use",
"description": "Control macOS desktop — mouse, keyboard, screenshots, windows, displays, clipboard. Native Quartz automation via usecomputer CLI.",
"version": "1.0.0",
"author": {
"name": "Talon"
},
"category": "automation",
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 · 187 lines scan A 53d9957aabc6
gettalon-talon-plugins is a plugin published in the GitHub repository gettalon/talon-plugins (6 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
mochi
A browser companion for AI assistants. Bundled MCP tools for Chrome automation, persistent project memory (Continuum chain), and an in-page hint modal — pair with the Mochi Chrome extension.
mochi
Mochi — a browser companion for AI assistants. Bundled browser automation, persistent project memory, and human-in-the-loop hint messaging.
browser-relay
Let agents use the Chrome you already have open and logged in through a Skill + CLI, locally or across machines.
byob
Claude Code plugins from the byob project.
devharness
Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.
chromeboost
ChromeBoost — drive your real Chrome from Claude Code with occlusion-aware cursor control and a movable HUD.