cf-agent-browser SKILL.md skillA

cf-agent-browser from haposoft/cafekit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add haposoft/cafekit/cf-agent-browser@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
haposoft/cafekit
Path
plugins/cf-codex/skills/agent-browser/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Oct 26, 2026
Size
9,988 bytes
Repository stars
54
License
none declared

AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase). Use when: Invoke to drive a real browser for navigation, screenshots, or DOM actions.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# agent-browser Skill

Browser automation CLI designed for AI agents. Uses "snapshot + refs" paradigm for 93% less context than Playwright MCP.

## Quick Start

```bash
# 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:

```bash
# 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 "user@example.com"
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 |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add haposoft/cafekit/cf-agent-browser@sha256:99961b90c28e5236

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ldr3isqgpvbtou4g.svg)](https://markdownregistry.com/a/art_ldr3isqgpvbtou4g)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 26, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-26 2284f49 9,988 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9988 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

haposoft/cafekit · 54 stars · license none declared · pushed 2026-11-05 · branch dev

API

GET https://markdownregistry.com/api/v1/artifacts/art_ldr3isqgpvbtou4g
GET https://markdownregistry.com/api/v1/resolve?ref=haposoft/cafekit/cf-agent-browser
GET https://markdownregistry.com/api/v1/blob/99961b90c28e523675e0ca45bc2dd975d5d4931abb09b4857ee2714d1265e65a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from haposoft/cafekit

AGENTS.md AGENTS.md file
haposoft/cafekit · AGENTS.md
git:20261018.54f438e · audit A · 54 stars
CLAUDE.md CLAUDE.md file
haposoft/cafekit · CLAUDE.md
git:20261018.30be9bd · audit B · 54 stars
llms.txt@cafekit-web/src/components/ui llms.txt file
haposoft/cafekit · cafekit-web/src/components/ui/llms.txt
git:20260203.5213074 · audit A · 54 stars
CLAUDE.md@evals/research/fixtures/khong-luu-khong-sua CLAUDE.md file
haposoft/cafekit · evals/research/fixtures/khong-luu-khong-sua/CLAUDE.md
git:20260930.3fa9f43 · audit B · 54 stars
CLAUDE.md@packages/spec/src/claude CLAUDE.md file
haposoft/cafekit · packages/spec/src/claude/CLAUDE.md
git:20261023.a626d73 · audit B · 54 stars
cf:adv SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/adv/SKILL.md · Interview until the user and the agent hold the same picture of the outcome, preview it, then deliver honest…
v1.0.0 · audit A · 54 stars
cf:agent-browser SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/agent-browser/SKILL.md · AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying…
v1.0.0 · audit A · 54 stars
cf:ai-multimodal SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/ai-multimodal/SKILL.md · Analyze images/audio/video/documentation with Gemini API. Use for vision analysis, transcription, OCR, design…
v1.0.0 · audit A · 54 stars
cf:ask SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/ask/SKILL.md · Answer questions with evidence. Use when the user asks about project behavior, source code, specs, docs, configuration…
v1.0.0 · audit A · 54 stars
cf:backend-development SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/backend-development/SKILL.md · Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT)…
v1.0.0 · audit A · 54 stars
cf:brainstorm SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/brainstorm/SKILL.md · Shape an unsettled piece of work into a decided one before anyone builds it. Use when the outcome is already agreed but…
v3.0.0 · audit A · 54 stars
cf:chrome-devtools SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/chrome-devtools/SKILL.md · Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis…
v1.1.0 · audit B · 54 stars

Every file in haposoft/cafekit

Browse by kind, by grade A, or by owner.