Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add lttr/claude-marketplace/plugin install browserWrote 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/lttr/claude-marketplace/pick)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/pick"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/pick/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/lttr/claude-marketplace/pick"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/pick.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 | $0.00036 | $0.01597 |
| Opus 5.5 | $0.00014 | $0.00639 |
| Sonnet 5.5 | $0.00007 | $0.00319 |
| Haiku 4.5 | $0.00004 | $0.00160 |
Grade B, and why
pick scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Dev host/port hint (from CLAUDE.md, if any): !`grep -rhoE 'https?://[a-zA-Z0-9.-]+:[0-9]+' CLAUDE.md .claude/CLAUDE.md 2>/dev/null | sort -u | head -3 || echo "No CLAUDE.md dev URL hint"` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(playwright-cli:*), Bash(google-chrome:*), Bash(open:*), Bash(curl:*), Bash(ss:*), Bash(lsof:*), Bash(seq:*), Bash(sleep:*), Bash(cat:*), Bash(npm:*), Bash(grep:*), Read, Glob How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pick
Context
- Current working directory: !
pwd - Package.json dev script (if exists): !
cat package.json 2>/dev/null | grep -E '"dev":|"start":' | head -2 || echo "No dev/start script" - Dev host/port hint (from CLAUDE.md, if any): !
grep -rhoE 'https?://[a-zA-Z0-9.-]+:[0-9]+' CLAUDE.md .claude/CLAUDE.md 2>/dev/null | sort -u | head -3 || echo "No CLAUDE.md dev URL hint" - LISTEN ports (candidate dev servers): !
{ ss -tlnH 2>/dev/null | awk '{print $4}' || lsof -nP -iTCP -sTCP:LISTEN 2>/dev/null | awk 'NR>1{print $9}'; } | grep -oE ':[0-9]+$' | tr -d ':' | sort -un | grep -vE '^(22|53|631)$' | head -10 || echo "none" - Debuggable browser on :9222 (Chrome OR Edge — both CDP): !
curl -s --max-time 1 http://localhost:9222/json/version 2>/dev/null | grep -oE '"Browser": *"[^"]*"' || echo "nothing on :9222"
Your task
Help the user pick an element from the browser. playwright-cli attaches to
any Chromium browser over CDP (Chrome, Edge, Electron) — there is no native
picker, so we inject a JS overlay and poll for the result.
Every command below runs in the named session -s=pick (the flag goes before
the command), so it never touches the user's other playwright-cli sessions.
Step 0: Preflight
${CLAUDE_PLUGIN_ROOT}/skills/playwright-cli/check.sh
If it fails, stop and relay its message to the user — it says what to install.
Step 1: Get a debuggable browser
- Reuse what's already on :9222 if the context shows one (the user's normal Chrome/Edge — best, keeps logged-in sessions). Skip to Step 1b.
- Else launch a fresh Chrome. Must be detached (
nohup … &) or it dies when the command returns.--ignore-certificate-errors --test-typehandles flaky dev TLS (e.g. self-signed*.localhosts). 9222 is often taken by Edge/Teams, so use a free port. The binary name differs per OS:google-chrome(Linux),"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"(macOS),chrome.exeormsedge.exe(Windows) — Edge takes the same flags.nohup google-chrome --remote-debugging-port=9223 \ --user-data-dir="$HOME/.chrome-debug-profile" \ --ignore-certificate-errors --test-type "<start-url>" \ </dev/null >/dev/null 2>&1 & until curl -s http://localhost:9223/json/version >/dev/null 2>&1; do sleep 0.3; done
What ships with it
1 file 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.
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 · 125 lines · 36 tokens per session scan B 0c962cc09dd6
pick is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 14d ago), licensed MIT. It adds 36 tokens to every session and 1,597 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
webui-code
Use this skill when generating or reviewing WebUI code. This skill contains knowledge on WebUI code following Chrome's Lit-element architecture and styling guidelines.
figma-to-webui
Recreate Figma design frames as production-level Chromium WebUI code following Chrome's Lit-element architecture and styling guidelines. Use when asked to create WebUI code from a Figma frame URL.
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
glassmorphism
Glassmorphism design system skill. Use when building frosted-glass UI components with blur, transparency, and layered depth effects.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
scrapling
A Python-based web-scraping workflow for fetching pages and extracting data, including pages that need JavaScript, login sessions, or protection handling. Web scraping means collecting information from websites by code.