Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Buzzmatic/awesome-agent-skillsnpx agentmods add skills/buzzmatic/awesome-agent-skills/agent-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/skills/buzzmatic/awesome-agent-skills/agent-browser)<a href="https://agentmods.dev/skills/buzzmatic/awesome-agent-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/buzzmatic/awesome-agent-skills/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/buzzmatic/awesome-agent-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/buzzmatic/awesome-agent-skills/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 | $0.00091 | $0.02515 |
| Opus 5.5 | $0.00036 | $0.01006 |
| Sonnet 5.5 | $0.00018 | $0.00503 |
| Haiku 4.5 | $0.00009 | $0.00251 |
Grade B, and why
agent-browser scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
| `execute` | Run arbitrary command sequences | --commands (JSON array) | How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser Skill
Headless browser automation using Playwright Python. Provides accessibility tree snapshots with @e# element references for deterministic interaction, screenshot capture, form filling, and multi-command execution sequences.
Quick Start
Scrape page content (prints to stdout, saves to output/):
python skills/agent-browser/scripts/browse.py \
--operation scrape \
--url "https://example.com"
With a custom output directory:
python skills/agent-browser/scripts/browse.py \
--output-dir output \
--operation screenshot \
--url "https://example.com" \
--full-page
Supported Operations
| Operation | Description | Key Parameters |
|---|---|---|
scrape |
Open page and get accessibility tree | --url |
screenshot |
Capture page screenshot | --url, --full-page |
snapshot |
Get element refs for interaction | --url, --interactive |
click |
Click an element | --url, --selector |
fill |
Fill a form input | --url, --selector, --text |
type |
Type text character by character | --url, --selector, --text |
execute |
Run arbitrary command sequences | --commands (JSON array) |
Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
--operation |
Yes | - | Operation type (see table above) |
--url |
Depends | - | Target URL (required for most operations) |
--output-dir |
No | output |
Directory to save output files (defaults to ./output/) |
--selector |
Depends | - | Element selector (@e1, CSS, or XPath) |
--text |
Depends | - | Text to fill/type |
--commands |
Depends | - | JSON array of commands for execute operation |
--full-page |
No | false | Full page screenshot |
--interactive |
No | false | Interactive elements only in snapshot |
--timeout |
No | 30000 | Command timeout in ms |
--profile |
No | - | Browser profile name for authenticated sessions (loads cookies from ./browser-profiles/<name>/) |
What ships with it
2 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 · 262 lines · 91 tokens per session scan B 7849324d4f51
agent-browser is a skill published in the GitHub repository Buzzmatic/awesome-agent-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 2,515 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.