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/talongit clone --depth 1 https://github.com/gettalon/talon-pluginsGrade A, and why
talon 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 yesterday.
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.
What it actually says
{
"name": "talon",
"description": "Talon — all-in-one plugin for Claude Code. Browser control, channels (22 adapters), computer use, AI dispatch, autoresearch, GitLab scrum.",
"version": "1.0.0",
"author": {
"name": "Talon"
},
"homepage": "https://github.com/gettalon/talon-plugins",
"repository": "https://github.com/gettalon/talon-plugins",
"license": "MIT",
"keywords": [
"talon",
"browser",
"channels",
"computer-use",
"ai-dispatch",
"autoresearch",
"gitlab"
]
}
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.
- yesterday First seen · 21 lines scan A 6fce3c12c998
talon 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.
claude-craft
Plugin marketplace listing 1 plugin: claude-craft.
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.