A browser-control tool for running Playwright, a program that opens and operates web browsers, from the command line. It can run browsers without displaying their windows and can manage multiple sessions.

Use it for browser-based tests, screenshots, web scraping, background browsing, and automated interaction with websites.

It automates browser work without requiring someone to operate a browser manually. This helps with checking interfaces, capturing pages, and collecting information from websites.

How chankov/agent-fleet configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chankov/agent-fleet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/chankov/agent-fleet/main/.pi/skills/bowser/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/chankov/agent-fleet

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chankov/agent-fleet/bowser/github.svg)](https://agentmods.dev/skills/chankov/agent-fleet/bowser)

Your own site

<a href="https://agentmods.dev/skills/chankov/agent-fleet/bowser"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/bowser/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chankov/agent-fleet/bowser"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/bowser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,563 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 25
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.01563
Opus 5.5	$0.00024	$0.00625
Sonnet 5.5	$0.00012	$0.00313
Haiku 4.5	$0.00006	$0.00156

Measured 2mo ago against content hash 753bd7cfe440, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bowser 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 2mo 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.

.pi/skills/bowser/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playwright Bowser

Purpose

Automate browsers using playwright-cli — a token-efficient CLI for Playwright. Runs headless by default, supports parallel sessions via named sessions (-s=), and doesn't load tool schemas into context.

Requirements

This skill drives the external Playwright Agent CLI (playwright-cli). It is not bundled with agent-fleet — install it once before using this skill (the guided setup checks for it when bowser is selected).

Node.js 20+
playwright-cli — install globally:

npm install -g @playwright/cli@latest
playwright-cli --help                 # verify it responds

Or run ad-hoc without a global install via npx playwright-cli <command>.

Browsers are downloaded automatically on first use; to pre-install explicitly:

playwright-cli install-browser               # default (chromium)
playwright-cli install-browser firefox       # a specific browser
playwright-cli install-browser --with-deps   # include system dependencies

Full install docs: https://playwright.dev/agent-cli/installation

When to use this vs Chrome DevTools MCP

This skill (playwright-cli) and the chrome-devtools-mcp pi extension are complementary, not redundant — they differ by tool model, not just headless-vs-headful (both can do either):

bowser / playwright-cli (this skill) — CLI-driven, headless-first, parallel named sessions, token-efficient (no tool schemas in context). It needs only Bash, so it works as a dispatched subagent under --no-extensions. Use it for automated, parallel, or background runtime-UI evidence and scraping.
web-debugger / chrome-devtools-mcp — live chrome_devtools__* tools (DOM/console/network/performance traces) for interactive headful debugging with a human in the loop. Those tools come from an always-on extension, so they are reachable in the main session or a coms peer, not a --no-extensions subagent. Use it to understand a failure in a running dev app.

Read the full file on GitHub · 146 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.

2mo ago First seen · 146 lines · 59 tokens per session scan A 753bd7cfe440

Subscribe to this mod's changes

bowser is a skill published in the GitHub repository chankov/agent-fleet (20 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 1,563 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 2026-08-31.

Browser automation

bowser next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bowserchankov/agent-fleet	Skill	20	12d ago	MIT	A	59	Claude Code
interactive-loginyc-software/qm	Skill	16k	yesterday	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	yesterday	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	yesterday	MIT	A	40	Claude Code

agent-fleet: Skill for Claude Code