Agent skill + Wayfern

If your agent has a shell, it has Wayfern.

One SKILL.md file
curl and a wf_ token
The same credits as the API

Some agents do not speak MCP, and some runs have no browser for a sign-in. Most of them can run curl.

The Wayfern skill is one SKILL.md file. It tells the agent which REST endpoint to call for a search, a page, a crawl or a screenshot, and to read the token from WAYFERN_API_TOKEN.

~/project · agent

$ curl -fsSL https://wayfern.com/skills/wayfern/SKILL.md \

-o ~/.agents/skills/wayfern/SKILL.md

SKILL.md saved · 4.6 kB

> Scrape example.com with the Wayfern skill. Give me the title.

Read~/.agents/skills/wayfern/SKILL.md

name: wayfern · POST /api/v1/scrape · 1 credit

Runcurl -sS https://api.wayfern.com/api/v1/scrape \

-H "Authorization: Bearer $WAYFERN_API_TOKEN" \

-d '{"url": "https://example.com", "formats": ["markdown"]}'

{"success": true,

"data": {"markdown": "# Example Domain\n\nThis domain is…",

"metadata": {"title": "Example Domain"}},

"credits": 1}

The title is “Example Domain”. 1 credit spent.

Setup

Install the file, set the token.

The skill works in any agent that loads SKILL.md folders. Other agents can read the file as instructions.

Install it for Claude Code

Claude Code loads skills from ~/.claude/skills. Cursor and Grok Build read this folder too.

bash

mkdir -p ~/.claude/skills/wayfern
curl -fsSL https://wayfern.com/skills/wayfern/SKILL.md -o ~/.claude/skills/wayfern/SKILL.md

2
Or for Codex and others

Codex, Cursor, VS Code, Gemini CLI and Kimi Code read ~/.agents/skills. For one repo, use .agents/skills.
bash

mkdir -p ~/.agents/skills/wayfern curl -fsSL https://wayfern.com/skills/wayfern/SKILL.md -o ~/.agents/skills/wayfern/SKILL.md
3
Set the token

Create a token on the Tokens page. Put it in the agent's environment, not in the skill file.
bash

export WAYFERN_API_TOKEN=wf_...

Ask

prompt

Use the Wayfern skill to scrape https://example.com and give me the title.

Other ways to connect

Plain curl

The skill teaches calls like this one. A script can run it as it is.

bash

curl -X POST https://api.wayfern.com/api/v1/scrape \
  -H "Authorization: Bearer $WAYFERN_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "formats": ["markdown"]}'

Other skills folders

Hermes Agent: hermes skills install with the SKILL.md URL. OpenClaw: ~/.openclaw/skills. Grok Build: ~/.grok/skills. VS Code: ~/.copilot/skills.

Route

One file, one token, no protocol.

The skill needs a shell, curl and a token. There is no MCP session to keep and no sign-in window.

Remote MCP OAuth sign-in: Works; For a client with a browser, the remote server signs in with OAuth.
MCP + token Authorization header: Works; If the agent also speaks MCP, the token header gives it the tools.
Agent skill SKILL.md: Best fit; SKILL.md in the agent's skills folder, with WAYFERN_API_TOKEN set.
REST API api.wayfern.com/api/v1: Works; The same REST calls from your own code.
Browser API Playwright over CDP: Works; Playwright scripts connect to a Wayfern browser over CDP with a link token.

Example tasks

Recipes

01

Read a page

“Use the Wayfern skill to read the setup page of our main dependency's docs and list the steps.”

POST /api/v1/scrape costs 1 credit a page.
02

Search an error

“Search Google for this error message with the skill and list the top five results.”

POST /api/search/v1 bills 2 credits for each provider page.
03

Crawl a docs site

“Start a crawl of docs.example.com, 50 pages at most. Poll it until it is done and save the pages as markdown.”

POST /api/v1/crawl bills 1 credit for each page. GET /api/v1/crawl/:id reads the status.
04

Save a screenshot

“Capture https://example.com as a full page and save the image to shots/home.png.”

POST /api/v1/screenshot costs 5 credits a capture.

Tools

What Agent skill can call

The same tools on every route, at the REST API rates. Every result reports credits_charged.

All tool inputs

scrape_page Fetch one page through an anti-detect browser and return clean markdown, HTML, links and metadata. The screenshot, pdf and json formats add +4 credits (once); summary adds +2. 1 credit / page
extract_data Extract structured data from one or more pages with a prompt and an optional JSON Schema. Re-running over pages already fetched is free. 1 credit / uncached source page
map_site List a site's URLs from its sitemaps and page links. 2 credits / 10 URLs
capture_screenshot Capture a clean image of a page: cookie banners and ads removed, lazy images loaded, tall pages captured end to end. Returns a short-lived download URL and an artifact key, not image bytes. Slices of a full page cost nothing extra; a fail_if_contains match is not charged. 5 credits / capture
brand_profile Identity, colours, logos, social links and company metadata for a domain. 10 credits / profile
site_styleguide Colours, typography, spacing, radii, shadows and the design tokens a site declares. 10 credits / site
site_fonts Font families, where each is served from, available weights, file formats and where they are used. 5 credits / site
crawl_site Start a bounded multi-page crawl. Returns a job id immediately and charges nothing up front; pages are billed as the crawl runs. 1 credit / successful page
crawl_status Poll a crawl started with crawl_site and read a page of its results. The pages were billed as they were crawled. Free
search_web Search Google, Bing, and DuckDuckGo. Returns ranked results, ads, provider failures, pagination, and related queries. 2 credits / provider page
list_search_engines List live provider ids and labels. Free

Good to know

Scopes: The REST calls need a token with the web and search scopes. New tokens have all four scopes by default.
Failed calls: Failed requests are not billed. Credits are reserved first and debited only when output exists.
Sandboxes: An agent sandbox must allow network access to api.wayfern.com for curl to work.