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 only-cli/ocnpx agentmods add plugins/only-cli/oc/marketplacegit clone --depth 1 https://github.com/only-cli/ocGrade A, and why
only-cli 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": "only-cli",
"owner": { "name": "only-cli" },
"plugins": [
{
"name": "only-cli",
"source": { "source": "github", "repo": "only-cli/oc" },
"description": "Browse websites from the terminal in a few hundred tokens",
"version": "0.5.0",
"homepage": "https://github.com/only-cli/oc",
"license": "MIT"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 15 lines scan A 7f278325d3e1
only-cli is a plugin published in the GitHub repository only-cli/oc (411 stars, last pushed 6d 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 2026-08-30.
Other plugins, from other repositories
familiar
AppleScript-powered Chrome control for macOS, packaged as a Claude Code skill.
familiar
Control your real macOS Google Chrome via AppleScript — tab-scoped browser automation without the DevTools Protocol or Playwright.
browser-harness
Direct browser control via CDP. Drives the user's real Chrome (or a Browser Use cloud browser) with coordinate clicks, screenshots, and Python helpers — no selector hunting. Requires the one-time browser-harness CLI install (see the skill's references/install.md).
cli
Run HeadlessX website, search, YouTube, and jobs workflows from the terminal.
docpull
Pull public web sources into Claude Code. Indexes static and server-rendered sites as local Markdown with conditional-GET caching, then exposes them as MCP tools. Local, browser-free, no API keys.
tandem
A shared Chrome browser (human + Claude, CDP + Playwright MCP) that learns how each site is navigated: the human drives with the mouse and clears captchas/logins, Claude operates over CDP, and tandem:map persists per-site navigation memory (durable locators, drift, auto-injection).