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 eddie-292/grapwork --skill agent-browsergit clone --depth 1 https://github.com/eddie-292/grapworkWrote 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/eddie-292/grapwork/agent-browser)<a href="https://agentmods.dev/skills/eddie-292/grapwork/agent-browser"><img src="https://agentmods.dev/badge/skills/eddie-292/grapwork/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/eddie-292/grapwork/agent-browser"><img src="https://agentmods.dev/badge/skills/eddie-292/grapwork/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 | $0.00042 | $0.02698 |
| Opus 5.5 | $0.00017 | $0.01079 |
| Sonnet 5.5 | $0.00008 | $0.00540 |
| Haiku 4.5 | $0.00004 | $0.00270 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
First-Time Setup (Important!)
Before using agent-browser for the first time, you MUST install the CLI tool and browser binary:
# Step 1: Install the agent-browser CLI globally
npm install -g agent-browser
# Step 2: Install the Chromium browser binary
agent-browser install
You only need to do this once.
Session Requirement (Critical!)
Always specify a session name when using agent-browser. Without it, you may encounter the error:
"Browser not launched. Call launch first."
There are two ways to specify a session:
- Environment variable (recommended for chained commands):
export AGENT_BROWSER_SESSION=mysession
agent-browser --headed open https://example.com
agent-browser snapshot -i
agent-browser click @e1
- Command-line flag:
agent-browser --session mysession --headed open https://example.com
agent-browser --session mysession snapshot -i
agent-browser --session mysession click @e1
The session name can be any string (e.g., taobao, google, test1). Using consistent session names allows you to maintain browser state across multiple commands.
Browser Mode
Mode Selection Rules:
- Virtual Machine / Remote Server: Use
--headlessmode (no display available) - Local Machine (Default): Use
--headedmode (visible browser window for better debugging) - User Request: Follow user's explicit preference (headless/无头模式 or headed/有头模式)
How to detect environment:
- Check
<env>section in system context for platform info - VM indicators: Linux without display, SSH session, Docker container, cloud server
- If uncertain, try
--headedfirst; if it fails with display error, fallback to--headless
Options:
--headed: Visible browser window (default for local machines)--headless: Invisible browser (default for VMs/servers, or when user requests)
Core Workflow
Every browser automation follows this pattern:
- Setup session:
export AGENT_BROWSER_SESSION=mysite - Navigate:
agent-browser --headed open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
What ships with it
9 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.
- references/authentication.md 4.9 KB
- references/commands.md 9.3 KB
- references/proxy-support.md 4.6 KB
- references/session-management.md 4.2 KB
- references/snapshot-refs.md 4.2 KB
- references/video-recording.md 3.5 KB
- templates/authenticated-session.sh 3.2 KB runs code
- templates/capture-workflow.sh 1.8 KB runs code
- templates/form-automation.sh 1.8 KB runs code
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 · 352 lines · 42 tokens per session scan A 4bd76b535aaa
agent-browser is a skill published in the GitHub repository eddie-292/grapwork (50 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 2,698 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 2026-08-30.
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…