surf

surf is a skill for Claude Code from vibesurf-ai/claude-surf. It costs 43 tokens per session (3,806 once invoked), scanned A, original, MIT.

A browser-automation entry point for browsing websites, extracting information, searching online, and interacting with pages or external apps. It delegates each task to a more specific browser action.

In plain words
What is it for?
Use it to browse pages, automate browser steps, fill forms, search or extract webpage data, and work with supported external applications.
Why use it?
It provides one starting point for browser tasks instead of requiring you to know the right action in advance.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions subagents.

Part of the surf plugin — 21 skills, 1 hook shipped together

Good fit Use it to browse pages, automate browser steps, fill forms, search or extract webpage data, and work with supported external applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vibesurf-ai/claude-surf/surf
Install

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.

Any agent
npx skills add vibesurf-ai/claude-surf --skill surf
Clone the repo
git clone --depth 1 https://github.com/vibesurf-ai/claude-surf

Made for: Claude Code.

Or install surf, the plugin that ships this one along with the rest of its 21 skills, 1 hook.

Wrote 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.

agentmods badge for surf

README.md
[![agentmods](https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/surf/github.svg)](https://agentmods.dev/skills/vibesurf-ai/claude-surf/surf)
Your own site
<a href="https://agentmods.dev/skills/vibesurf-ai/claude-surf/surf"><img src="https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/surf/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.

agentmods 80×15 button for surf

Your own site · 80×15
<a href="https://agentmods.dev/skills/vibesurf-ai/claude-surf/surf"><img src="https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/surf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.03806
Opus 5 $0.00022 $0.01903
Sonnet 5 $0.00009 $0.00761
Haiku 4.5 $0.00004 $0.00381

Measured 10d ago against content hash a822b42b99e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

surf scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> **Check manually:** `curl $VIBESURF_ENDPOINT/health` (default: http://127.0.0.1:9335)
skills/surf/SKILL.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Surf - VibeSurf Browser Automation

Overview

Control real browsers through VibeSurf. This skill delegates to specialized sub-skills.

🚨 VIBESURF STATUS (Auto-detected at session start)

Check the <SURF_SKILLS> status at the TOP of this context:

  • Status: running → Proceed with surf skills
  • Status: not_running → Ask user to run vibesurf (NEVER run it yourself)

Check manually: curl $VIBESURF_ENDPOINT/health (default: http://127.0.0.1:9335)

How to Call VibeSurf API

VibeSurf exposes three core HTTP endpoints. All requests go to the configured endpoint (check the status line above for the actual endpoint):

1. List Available Actions

GET $VIBESURF_ENDPOINT/api/tool/search?keyword={optional_keyword}

Returns all available VibeSurf actions.

2. Get Action Parameters

GET $VIBESURF_ENDPOINT/api/tool/{action_name}/params

Returns JSON schema for the action's parameters.

3. Execute Action

POST $VIBESURF_ENDPOINT/api/tool/execute
Content-Type: application/json

{
  "action_name": "action_name_here",
  "parameters": {
    // action-specific parameters
  }
}

Workflow:

  1. Search for action → Get action name
  2. Get params schema → See required/optional parameters
  3. Execute → Call with parameters

⚠️ CRITICAL: Parameter Error Handling

ALWAYS call GET /api/tool/{action_name}/params before executing ANY action if you are unsure about parameters.

When you encounter a parameter error:

  1. STOP - Do not guess or make up parameters
  2. CALL GET /api/tool/{action_name}/params to get the exact schema
  3. READ the response to identify required vs optional parameters
  4. RETRY with correct parameters

Never blindly retry with incorrect parameters. Always fetch the schema first!

Which Skill to Use

Task Type Use Skill Action Name
AI web search search skill_search
Fetch URL content as markdown fetch skill_fetch
Extract lists/tables js_code skill_code
Extract page content crawl skill_crawl
Summarize page summary skill_summary
Stock/financial data finance skill_finance
Trending news trend skill_trend
Screenshot screenshot skill_screenshot
Precise browser control browser browser.* actions
Task-oriented automation (sub-agent) browser-use execute_browser_use_agent
Social Media Platform APIs website-api get_website_api_params, call_website_api
Pre-built workflows workflows search_workflows, execute_workflow
Gmail/GitHub/Slack integrations get_all_toolkit_types, execute_extra_tool
LLM profile settings config-llm config/llm-profiles/*
MCP server config config-mcp config/mcp-profiles/*
VibeSurf key/workflows config-vibesurf vibesurf/verify-key, vibesurf/import-workflow
Composio key/toolkits config-composio composio/verify-key, composio/toolkits
Schedule workflows config-schedule schedule/*
File upload/download file /api/files/*
Voice/ASR configuration config-voice /api/voices/*

Read the full file on GitHub · 311 lines

Changes

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.

  1. 10d ago First seen · 311 lines · 43 tokens per session scan A a822b42b99e3

Subscribe to this mod's changes

surf is a skill published in the GitHub repository vibesurf-ai/claude-surf (24 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 3,806 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories