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.
npx skills add musingfox/cc-plugins --skill agent-browsergit clone --depth 1 https://github.com/musingfox/cc-pluginsWrote 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/skills/musingfox/cc-plugins/agent-browser)<a href="https://agentmods.dev/skills/musingfox/cc-plugins/agent-browser"><img src="https://agentmods.dev/badge/skills/musingfox/cc-plugins/agent-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/skills/musingfox/cc-plugins/agent-browser"><img src="https://agentmods.dev/badge/skills/musingfox/cc-plugins/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01269 |
| Opus 5.5 | $0.00023 | $0.00508 |
| Sonnet 5.5 | $0.00011 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
agent-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 10d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser
Overview
agent-browser is a CLI that gives AI agents direct control over headless browsers. It uses a ref-based interaction model: every interactive element receives a unique reference identifier (@e1, @e2, etc.) derived from the accessibility tree. This enables deterministic, token-efficient browser automation without fragile CSS selectors.
Prerequisites
Ensure agent-browser is installed and the browser binary is available:
# Check installation
agent-browser --version
# Install globally
npm install -g agent-browser
agent-browser install
# On Linux, include system dependencies
agent-browser install --with-deps
Core Workflow: The Ref Cycle
Every browser interaction follows a strict cycle:
open URL → snapshot → read refs → interact → re-snapshot → repeat
- Navigate to the target page with
open - Snapshot to obtain the accessibility tree with refs
- Read the snapshot output — identify target elements by their refs
- Interact with elements using their refs (
click @e1,fill @e2 "text") - Re-snapshot when the page changes (see Re-snapshot Rules)
Snapshot Modes
The snapshot command is the primary inspection tool. Choose the right mode:
snapshot -i— Interactive elements only (buttons, inputs, links). Use as default.snapshot -i -C(uppercase C) — Include cursor-interactive elements (divs with onclick). Use when expected elements are missing from-i. Note:-C(cursor-interactive) is distinct from-c(compact).snapshot -c— Compact output. Reduces token usage on large pages.snapshot -d N— Limit tree depth to N levels. Use for deeply nested DOMs.snapshot -s "selector"— Scope to a CSS selector. Focus on a specific page section.
Combine flags freely: agent-browser snapshot -i -c -d 3 for compact, shallow, interactive-only output.
Element Interaction Patterns
Text Input
fill @eN "text"— Clears existing content, then types. Use for replacing field values.type @eN "text"— Appends without clearing. Use for adding to existing content.
What ships with it
1 file beside SKILL.md 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.
- 10d ago Changed · -23 lines · +1 tokens per session 024ecee4f23f
- 1mo ago Changed · +1 lines 8ebe94207a50
- 1mo ago First seen · 147 lines · 56 tokens per session scan A ee5f17106fc9
agent-browser is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,269 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.