bowser

An agent for controlling a web browser without a visible user interface using Playwright, a browser automation tool.

In plain words
What is it for?
Use it to test web interfaces, take screenshots, scrape pages, inspect browser output, or run several browser sessions at once.
Why use it?
It makes repeatable browser actions and checks possible without manually using the site, while preserving screenshots and other evidence when required.

Agent

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.

agentmods
npx agentmods add agents/chankov/agent-fleet/bowser
Clone the repo
git clone --depth 1 https://github.com/chankov/agent-fleet
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.00298
Opus 5 $0.00029 $0.00149
Sonnet 5 $0.00012 $0.00060
Haiku 4.5 $0.00006 $0.00030

Measured 2d ago against content hash 81d7745c86f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.versions/0.0.1/agents/bowser.md · 26 lines

What it actually says

Playwright Bowser Agent

Purpose

You are a headless browser automation agent. Use the bowser skill to execute browser requests via the playwright-cli tool.

Workflow

  1. Execute the /bowser skill with the user's prompt — derive a named session and run playwright-cli commands.
  2. For any runtime-ui acceptance assertion, save concrete evidence artifacts (screenshot, DOM dump, console/network log, or trace summary) under .pi/agent-sessions/artifacts/evidence/ when running in agent-hub. Create the directory if needed.
  3. Report the artifact path(s) in the structured return evidence for each proven runtime-ui assertion. Do not mark a runtime-ui assertion proven from prose alone; name the saved artifact path.
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. 2d ago First seen · 26 lines · 58 tokens per session scan A 81d7745c86f4

Subscribe to this mod's changes

bowser is an agent published in the GitHub repository chankov/agent-fleet (10 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 298 once invoked, about $0.0003 per session on Opus 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.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

mcp

The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.

DuvInc/duvlify · 34 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

dogfood-persona

Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…

kamiazya/whiteboard · 86 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens