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.
git clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEBWrote 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/plugins/itamarzand88/cli-anything-web/cli-anything-web-plugin)<a href="https://agentmods.dev/plugins/itamarzand88/cli-anything-web/cli-anything-web-plugin"><img src="https://agentmods.dev/badge/plugins/itamarzand88/cli-anything-web/cli-anything-web-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/itamarzand88/cli-anything-web/cli-anything-web-plugin"><img src="https://agentmods.dev/badge/plugins/itamarzand88/cli-anything-web/cli-anything-web-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cli-anything-web 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 1mo 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.
What it actually says
{
"name": "cli-anything-web",
"version": "0.14.3",
"description": "CLI-Anything for the Web: Generate agent-native CLIs for closed-source web apps via network traffic analysis",
"author": {
"name": "Itamar",
"url": "https://github.com/ItamarZand88/CLI-Anything-WEB"
},
"license": "MIT",
"keywords": [
"cli-generation",
"web-automation",
"agent-native",
"reverse-engineering",
"playwright-cli",
"traffic-capture"
]
}
What it installs
The manifest is a name and a version. 6 skills, 6 commands, 4 agents, 1 MCP server travel with it, and installing the plugin installs all of them — 862 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill methodology A 65 tokens
- Skill standards A 73 tokens
- Skill testing A 55 tokens
- Skill boilerplate A 60 tokens
- Skill gap-analyzer A 62 tokens
- Skill capture B 57 tokens
- Command cli-anything-web A 42 tokens
- Command cli-anything-web:validate A 39 tokens
- Command cli-anything-web:test A 22 tokens
- Command cli-anything-web:list A 20 tokens
- Command cli-anything-web:refine A 43 tokens
- Command cli-anything-web:record A 29 tokens
- Agent cross-cli-consistency-checker A 71 tokens
- Agent output-ux-reviewer A 85 tokens
- Agent traffic-fidelity-reviewer A 59 tokens
- Agent harness-compliance-reviewer B 80 tokens
- MCP server chrome-devtools A not measured
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.
- 1mo ago First seen · 19 lines scan A 2fdcbc3e0c62
cli-anything-web is a plugin published in the GitHub repository ItamarZand88/CLI-Anything-WEB (232 stars, last pushed 4d 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
webcmd
Self-learning browser infrastructure for AI agents: live browser control plus local sitemap memory that makes repeat runs faster and cheaper.
cc-websearch
DDG-powered WebSearch and WebFetch replacement for Claude Code.
webshare
Official Webshare proxy skills: manage proxies with the webshare CLI, optimize a pool for a target site, build Playwright scrapers, and audit proxy spend.
webshare
Official Webshare proxy skills: manage proxies with the webshare CLI, optimize a pool for a target site, build Playwright scrapers, and audit proxy spend.
elnora-platform
Elnora AI Platform CLI and skills.
qirabot
Drive any GUI with natural language — click, type, extract, and verify on web browsers, Android, iOS, desktop apps, and games.