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.
npx skills add nebari-dev/pi-coding-agent-pack --skill web-browsergit clone --depth 1 https://github.com/nebari-dev/pi-coding-agent-packWrote 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/nebari-dev/pi-coding-agent-pack/web-browser)<a href="https://agentmods.dev/skills/nebari-dev/pi-coding-agent-pack/web-browser"><img src="https://agentmods.dev/badge/skills/nebari-dev/pi-coding-agent-pack/web-browser/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/nebari-dev/pi-coding-agent-pack/web-browser"><img src="https://agentmods.dev/badge/skills/nebari-dev/pi-coding-agent-pack/web-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.00744 |
| Opus 5.5 | $0.00025 | $0.00298 |
| Sonnet 5.5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
web-browser 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Browser Skill
Minimal CDP tools for collaborative site exploration.
Start Chrome
./scripts/start.js # Fresh profile
./scripts/start.js --profile # Copy your profile (cookies, logins)
Start Chrome on :9222 with remote debugging.
start.js auto-detects Chrome/Chromium, including Playwright-managed binaries under /opt/ms-playwright and ~/.cache/ms-playwright. Use CHROME_BIN to force a path.
Navigate
./scripts/nav.js https://example.com
./scripts/nav.js https://example.com --new
./scripts/nav.js https://idp.example/auth --url-contains keycloak
Navigate current tab or open new tab.
Targeting flags (supported by nav/eval/screenshot/click/type/wait):
--url-contains <fragment>: select tab whose URL contains fragment--target-id <id>: use specific CDP target id--wait-new-tab: wait for a newly opened tab/page (popup/new-tab auth flows)--timeout-ms <ms>: override timeout
Evaluate JavaScript
./scripts/eval.js 'document.title'
./scripts/eval.js 'document.querySelectorAll("a").length'
./scripts/eval.js --url-contains keycloak 'location.href'
Execute JavaScript in selected tab (async context). Be careful with string escaping; single quotes are easiest.
First-class click/type/wait helpers
./scripts/click.js '#kc-login'
./scripts/type.js '#username' 'nick'
./scripts/type.js '#password' 'ChangeMe1234!'
./scripts/wait.js --url-contains '/hub/home'
./scripts/wait.js --wait-new-tab --url-contains keycloak
These helpers reduce brittle one-off JS snippets and improve auth-flow reliability.
Screenshot
./scripts/screenshot.js
./scripts/screenshot.js --url-contains '/hub/home'
Screenshot selected viewport; prints temp file path.
Pick Elements
./scripts/pick.js "Click the submit button"
Interactive element picker. Click to select, Cmd/Ctrl+Click for multi-select, Enter to finish.
Dismiss Cookie Dialogs
./scripts/dismiss-cookies.js # Accept cookies
./scripts/dismiss-cookies.js --reject # Reject cookies (where possible)
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/cdp.js 5.1 KB runs code
- scripts/click.js 2.7 KB runs code
- scripts/dismiss-cookies.js 14 KB runs code
- scripts/eval.js 1.5 KB runs code
- scripts/logs-tail.js 1.9 KB runs code
- scripts/nav.js 1.8 KB runs code
- scripts/net-summary.js 2.5 KB runs code
- scripts/package-lock.json 756 B
- scripts/package.json 68 B
- scripts/page-target.js 2.6 KB runs code
- scripts/pick.js 5.4 KB runs code
- scripts/screenshot.js 1.2 KB runs code
- scripts/start.js 3.7 KB runs code
- scripts/type.js 2.1 KB runs code
- scripts/wait.js 2.0 KB runs code
- scripts/watch.js 7.2 KB runs code
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 · 114 lines · 62 tokens per session scan A 004bbfd258ba
web-browser is a skill published in the GitHub repository nebari-dev/pi-coding-agent-pack (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 62 tokens to every session and 744 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.
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…