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/showme)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/showme"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/showme/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/showme"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/showme.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 | $0.00070 | $0.00759 |
| Opus 5.5 | $0.00028 | $0.00304 |
| Sonnet 5.5 | $0.00014 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
showme 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
showme
Drive a headed browser to the state the user described, then hand them the live window. You do the setup, they do the exploring.
This skill only adds the headed, leave-open, hand-over wrapper. For the actual driving (navigate, snapshot, click, fill, log in), load the playwright-cli skill and follow it.
Steps
-
Preflight. Run
${CLAUDE_PLUGIN_ROOT}/skills/playwright-cli/check.sh. If it fails, relay its message to the user and stop. Do not fall back to another automation tool. -
Work out the target. From context, find the URL (production, staging, or
localhost:PORT), the preconditions that define the state, and the point of interest. If the app is this repo's and its dev server is not running, start it first. Ask one short question only when the target is genuinely ambiguous. -
Open a headed, named session. Every later command carries the same
-s=showme.playwright-cli -s=showme open --headed <url>If no window appears, a
showmesession is already running headless. Close it withplaywright-cli -s=showme closeand reopen.playwright-cli listshows every session and whether it is headed. -
Drive to the state with the snapshot-and-ref loop from
playwright-cli, stopping just before the point of interest. -
Verify before handing over. When the state is a claim to confirm (a bug, a regression, "X happens when you do Y"), trigger the key action yourself and check the outcome, as long as it is non-destructive. Never hand over a window that "should" show something you have not seen it show.
- It reproduced: reset to just before the action (reload or undo) so the user can trigger it themselves, then hand over and say you confirmed it.
- It did not reproduce: stop and tell the user the claim did not hold, with what you did and what happened instead of the expected result. Catching this here saves the user a dead-end click-through.
- The action is destructive, or the state is open-ended exploration: leave the action to the user and hand over.
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 Changed · -11 lines · -58 tokens per session f1fb5705c3b1
- 1mo ago First seen · 57 lines · 128 tokens per session scan A cad95e511527
showme is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 14d ago), licensed MIT. It adds 70 tokens to every session and 759 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
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.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, extract information from web pages, mock network requests, manage browser…
browser
Browser automation — setup the bsession environment, fetch info from a website (one-shot), create scripted automations (one-shot or recurring), or debug existing sessions. Works from any repo.
agent-browser
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection.
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
playwright-skill
Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD (GitHub Actions, GitLab, CircleCI, Azure, Jenkins), framework recipes (React, Next.js, Vue, Angular), and migration guides from…