pi-vs-claude-code is a collection of customized Pi Coding Agent instances used to compare an open-source coding agent with Claude Code. It is for exploring agent interfaces, orchestration, safety auditing, and integrations between coding agents. The catalogue entries are examples of the customized agent workflows in the collection.
Borrowing it
Nothing to install: this file belongs to disler/pi-vs-claude-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/disler/pi-vs-claude-code/main/.pi/skills/bowser/SKILL.mdgit clone --depth 1 https://github.com/disler/pi-vs-claude-codeWrote 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.
[](https://agentmods.dev/skills/disler/pi-vs-claude-code/bowser)<a href="https://agentmods.dev/skills/disler/pi-vs-claude-code/bowser"><img src="https://agentmods.dev/badge/skills/disler/pi-vs-claude-code/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.
<a href="https://agentmods.dev/skills/disler/pi-vs-claude-code/bowser"><img src="https://agentmods.dev/badge/skills/disler/pi-vs-claude-code/bowser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01131 |
| Opus 5.5 | $0.00024 | $0.00452 |
| Sonnet 5.5 | $0.00012 | $0.00226 |
| Haiku 4.5 | $0.00006 | $0.00113 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- bowser — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 115 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.
Key Details
- Headless by default — pass
--headedtoopento see the browser - Parallel sessions — use
-s=<name>to run multiple independent browser instances - Persistent profiles — cookies and storage state preserved between calls
- Token-efficient — CLI-based, no accessibility trees or tool schemas in context
- Vision mode (opt-in) — set
PLAYWRIGHT_MCP_CAPS=visionto receive screenshots as image responses in context instead of just saving to disk
Sessions
Always use a named session. Derive a short, descriptive kebab-case name from the user's prompt. This gives each task a persistent browser profile (cookies, localStorage, history) that accumulates across calls.
# Derive session name from prompt context:
# "test the checkout flow on mystore.com" → -s=mystore-checkout
# "scrape pricing from competitor.com" → -s=competitor-pricing
# "UI test the login page" → -s=login-ui-test
playwright-cli -s=mystore-checkout open https://mystore.com --persistent
playwright-cli -s=mystore-checkout snapshot
playwright-cli -s=mystore-checkout click e12
Managing sessions:
playwright-cli list # list all sessions
playwright-cli close-all # close all sessions
playwright-cli -s=<name> close # close specific session
playwright-cli -s=<name> delete-data # wipe session profile
Quick Reference
Core: open [url], goto <url>, click <ref>, fill <ref> <text>, type <text>, snapshot, screenshot [ref], close
Navigate: go-back, go-forward, reload
Keyboard: press <key>, keydown <key>, keyup <key>
Mouse: mousemove <x> <y>, mousedown, mouseup, mousewheel <dx> <dy>
Tabs: tab-list, tab-new [url], tab-close [index], tab-select <index>
Save: screenshot [ref], pdf, screenshot --filename=f
Storage: state-save, state-load, cookie-*, localstorage-*, sessionstorage-*
Network: route <pattern>, route-list, unroute, network
DevTools: console, run-code <code>, tracing-start/stop, video-start/stop
Sessions: -s=<name> <cmd>, list, close-all, kill-all
Config: open --headed, open --browser=chrome, resize <w> <h>
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.
- 1mo ago First seen · 115 lines · 59 tokens per session scan A ffabb1dc974a
bowser is a skill published in the GitHub repository disler/pi-vs-claude-code (1,716 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,131 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…