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 manhvann/codexkit --skill agent-browsergit clone --depth 1 https://github.com/manhvann/codexkitWrote 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/manhvann/codexkit/agent-browser)<a href="https://agentmods.dev/skills/manhvann/codexkit/agent-browser"><img src="https://agentmods.dev/badge/skills/manhvann/codexkit/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/manhvann/codexkit/agent-browser"><img src="https://agentmods.dev/badge/skills/manhvann/codexkit/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 | $0.00038 | $0.02215 |
| Opus 5.5 | $0.00015 | $0.00886 |
| Sonnet 5.5 | $0.00008 | $0.00443 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
ck: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 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.
This is a copy
91% identical to vc-agent-browser — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser Skill
Browser automation CLI designed for AI agents. Uses "snapshot + refs" paradigm for 93% less context than Playwright MCP.
Quick Start
# Install globally
npm install -g agent-browser
# Download Chromium (one-time)
agent-browser install
# Linux: include system deps
agent-browser install --with-deps
# Verify
agent-browser --version
Core Workflow
The 4-step pattern for all browser automation:
# 1. Navigate
agent-browser open https://example.com
# 2. Snapshot (get interactive elements with refs)
agent-browser snapshot -i
# Output: button "Sign In" @e1, textbox "Email" @e2, ...
# 3. Interact using refs
agent-browser fill @e2 "[email protected]"
agent-browser click @e1
# 4. Re-snapshot after page changes
agent-browser snapshot -i
When to Use (vs chrome-devtools)
| Use agent-browser | Use chrome-devtools |
|---|---|
| Long autonomous AI sessions | Quick one-off screenshots |
| Context-constrained workflows | Custom Puppeteer scripts needed |
| Video recording for debugging | WebSocket full frame debugging |
| Cloud browsers (Browserbase) | Existing workflow integration |
| Multi-tab handling | Need Sharp auto-compression |
| Self-verifying build loops | Session with auth injection |
Token efficiency: ~280 chars/snapshot vs 8K+ for Playwright MCP.
Command Reference
Navigation
agent-browser open <url> # Navigate to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser
Analysis (Snapshot)
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
agent-browser snapshot -c # Compact output
agent-browser snapshot -d 3 # Limit depth
agent-browser snapshot -s "nav" # Scope to CSS selector
Interactions (use @refs from snapshot)
agent-browser click @e1 # Click element
agent-browser dblclick @e1 # Double-click
agent-browser fill @e2 "text" # Clear and fill input
agent-browser type @e2 "text" # Type without clearing
agent-browser press Enter # Press key
agent-browser hover @e1 # Hover over element
agent-browser check @e3 # Check checkbox
agent-browser uncheck @e3 # Uncheck checkbox
agent-browser select @e4 "opt" # Select dropdown option
agent-browser scroll @e1 # Scroll element into view
agent-browser scroll down 500 # Scroll page by pixels
agent-browser drag @e1 @e2 # Drag from e1 to e2
agent-browser upload @e5 file.pdf # Upload file
What ships with it
3 files 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.
- 1mo ago First seen · 295 lines · 38 tokens per session scan A d128c0e308ad
ck:agent-browser is a skill published in the GitHub repository manhvann/codexkit (89 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,215 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to vc-agent-browser, differing in 13 lines, and is treated as a copy.
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 and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…