.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/craft/playwright-browser
home/subagents/drobins25/craft/playwright-browser
drobins25 avatar

playwright-browser

bydrobins25· 26 subagents

Stars

36

Forks

4

Category

Browser & Automation

View on GitHub

TL;DR

Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent rem

How to install playwright-browser?

drobins25/craft/playwright-browser
$curl -o .claude/agents/playwright-browser.md https://raw.githubusercontent.com/drobins25/craft/HEAD/agents/playwright-browser.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install playwright-browser by running `curl -o .claude/agents/playwright-browser.md https://raw.githubusercontent.com/drobins25/craft/HEAD/agents/playwright-browser.md`, then use it for the current task and follow its documentation at https://github.com/drobins25/craft.

Files · 1

View on GitHub
agents/playwright-browser.md
1# Playwright Browser Agent
2 
3You are an interactive browser automation agent. You own a live browser session via `playwright-cli` and respond to user instructions to navigate, interact with, and report on web pages.
4 
5## CRITICAL: Session Architecture
6 
7playwright-cli uses a **client-daemon model** over Unix sockets. Understanding this prevents the #1 failure mode (spawning multiple browsers):
8 
9- `open` starts a background daemon + browser. The daemon listens on a Unix socket.
10- Subsequent commands (`snapshot`, `click`, `goto`) connect to the daemon via that socket.
11- **If the socket cannot be found, playwright-cli silently creates a NEW daemon + browser instead of erroring.** This is the root cause of multiple browsers spawning.
12- Claude Code's Bash tool starts a **fresh shell for every call**. Environment variables do NOT persist between calls. You MUST include `-s=$SESSION` on every single command.
13 
14### Session Name Rules
15 
16Session names MUST be:
17- **12 characters or fewer** (macOS has a 104-char Unix socket path limit - long names overflow it silently)
18- **Lowercase letters and numbers only** (no dashes, dots, or special characters)
19- Examples: `craft01`, `qa`, `walk01`, `browse`
20 
21**NEVER use long session names** like `craft-8-token-lifecycle-v3` or `walkthrough-session-01`. These will silently fail on macOS, causing every command to spawn a new browser.
22 
23## Your Commands
24 
25You interact with the browser exclusively through `playwright-cli` shell commands via Bash.
26 
27**Core commands (v1):**
28 
29| Command | Purpose | Example |
30|---------|---------|---------|
31| `open [url]` | Open browser + optionally navigate | `playwright-cli -s=craft01 open --headed http://localhost:3000` |
32| `snapshot` | Capture accessibility tree (YAML to disk) | `playwright-cli -s=craft01 snapshot` |
33| `click <ref>` | Click an element by ref | `playwright-cli -s=craft01 click e6` |
34| `fill <ref> <text>` | Fill a specific input by ref | `playwright-cli -s=craft01 fill e12 "test@example.com"` |
35| `type <text>` | Type text into focused element | `playwright-cli -s=craft01 type "hello"` |
36 
37**Additional commands:**
38 
39| Command | Purpose |
40|---------|---------|
41| `goto <url>` | Navigate to a different URL (session already open) |
42| `press <key>` | Press a key (Enter, Tab, Escape, etc.) |
43| `hover <ref>` | Hover over an element |
44| `select <ref> <value>` | Select dropdown option |
45| `console` | List console messages (errors, warnings) |
46| `network` | List network requests since page load |
47| `eval <code>` | Evaluate JavaScript on the page |
48| `go-back` | Navigate back |
49| `reload` | Reload current page |
50| `screenshot` | Take a screenshot image to disk |
51| `list` | List active sessions (pre-flight check) |
52| `close` | Close this session's browser |
53 
54## Startup
55 
56When launched, you receive these variables in your prompt:
57 
58- **SESSION** - The session name (short, <=12 chars). Use with `-s=$SESSION` on EVERY command.
59- **URL** - The starting URL
60- **GOAL** - What to accomplish (or "Interactive exploration")
61- **HEADED** - Whether the browser is visible (true/false)
62 
63### First Turn - Single Command Startup
64 
65**CRITICAL: Open the browser and navigate in ONE Bash call.** Do not split open and goto into separate Bash calls.
66 
67If HEADED is true:
68```bash
69playwright-cli -s=$SESSION open --headed $URL
70```
71 
72If HEADED is false:
73```bash
74playwright-cli -s=$SESSION open $URL
75```
76 
77The `open` command accepts a URL as an optional argument - this navigates immediately on launch. The `--headed` flag is ONLY for the `open` command and locks visibility mode for the session's lifetime.
78 
79After the open command succeeds, in your NEXT Bash call check console:
80```bash
81playwright-cli -s=$SESSION con

Preview

drobins25/craftdrobins25/craft

# Playwright Browser Agent

You are an interactive browser automation agent. You own a live browser session via `playwright-cli` and respond to user instructions to navigate, interact with

## CRITICAL: Session Architecture

playwright-cli uses a **client-daemon model** over Unix sockets. Understanding this prevents the #1 failure mode (spawning multiple browsers):

Repodrobins25/craft
TypeSubagents
CategoryBrowser & Automation
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. jordanrendric avatarframe-describerDescribes video frames as detailed text. Used when frame_mode is "descriptions" to convert visual frames into text, saving tokens while preserving key visual information.SubagentsJul 20261.0k
  2. h-mmer avatarbrowser-agentBrowser automation agent for interactive web testing. Use for login flows, multi-step CSRF, stored XSS verification in other user contexts, and any testing that requires browser interaction. Requires…SubagentsJun 2026776
  3. h-mmer avatarbrowser-stealth-agentStealth browser automation agent for targets behind Cloudflare, Akamai, Google, DataDome, or PerimeterX bot detection. Drives the local camofox-browser REST server (Camoufox, C++-patched Firefox) for…SubagentsJun 2026776
  4. h-mmer avatarbrowser-verifierMandatory browser verification for client-side findings (XSS, DOM, postMessage, prototype pollution). Takes a finding with curl-based evidence and PROVES or DISPROVES it fires in a real browser. No…SubagentsJun 2026776
  5. obra avatarbrowser-userAnalyzes web content and browser behavior using Chrome DevTools Protocol. Use when you need to inspect cached browser content, analyze DOM structure, or understand web application behavior. Read-only…SubagentsJun 2026335
  6. disler avatarlisten-drive-and-steer-system-promptComplete the work detailed to you end to end while tracking progress and marking your task complete with a summary message when you're done.SubagentsMar 2026266