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/m4ttstack/fast-browserWrote 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/m4ttstack/fast-browser/fast-browser)<a href="https://agentmods.dev/plugins/m4ttstack/fast-browser/fast-browser"><img src="https://agentmods.dev/badge/plugins/m4ttstack/fast-browser/fast-browser/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/m4ttstack/fast-browser/fast-browser"><img src="https://agentmods.dev/badge/plugins/m4ttstack/fast-browser/fast-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
fast-browser 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 today.
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": "fast-browser",
"version": "0.1.14",
"description": "Fast Playwright browser automation for Claude Code and Codex",
"author": {
"name": "Matthew Goodwin"
},
"license": "MIT",
"skills": "./skills/",
"mcpServers": {
"fast-browser": {
"command": "node",
"args": [
"${CLAUDE_PLUGIN_ROOT}/bin/fast-browser-mcp.mjs"
]
}
}
}
What it installs
The manifest is a name and a version. 7 skills, 1 agent, 1 MCP server travel with it, and installing the plugin installs all of them — 301 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill fast-browsing A 25 tokens
- Skill capturing-flows A 48 tokens
- Skill composing-evidence A 68 tokens
- Skill reviewing-flows A 46 tokens
- Skill annotating-screenshots A 47 tokens
- Skill browser-macros A 25 tokens
- Skill mine-macros A 21 tokens
- Agent browser-driver A 21 tokens
- MCP server fast-browser 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.
- today Changed · +8 lines e85c2777c44a
- yesterday Changed ad5e2b937cac
- 3d ago Changed 5334986dac75
- 5d ago Changed 23b35b4781e7
- 8d ago Changed f4c6fa8b46c2
- 17d ago Changed 334a595448d8
- 18d ago Changed 7efc675ea34f
- 21d ago Changed 464e893bd3cc
- 28d ago Changed 610770fdbe92
- 1mo ago First seen · 11 lines scan A 8396c223bf9b
fast-browser is a plugin published in the GitHub repository m4ttstack/fast-browser (0 stars, last pushed today), 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
webcmd
Self-learning browser infrastructure for AI agents: live browser control plus local sitemap memory that makes repeat runs faster and cheaper.
rawtrace-mcp
Passive Chromium CDP capture: baselines, incremental changes, and queryable browser history.
familiar
Control your real macOS Google Chrome via AppleScript — tab-scoped browser automation without the DevTools Protocol or Playwright.
agentos-chrome-cdp
Control exact logged-in Chrome profiles with a Codex-compatible browser API.
claude-in-chrome
Drive your real, logged-in Chrome from Claude Code, and list tabs across readable Chrome and Chromium profiles. Exposes the extension's browser tools through the Claude in Chrome bridge and adds a read-only listopentabs tool backed by local session data. Driving requires the connected extension and a running Chrome.
browser-test
E2E browser test pipeline for Claude Code: author, refine, compile, and run Playwright tests using browser automation.