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 gw-space/claude-skillbelt/plugin install skillbeltWrote 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/gw-space/claude-skillbelt/browser-pane)<a href="https://agentmods.dev/skills/gw-space/claude-skillbelt/browser-pane"><img src="https://agentmods.dev/badge/skills/gw-space/claude-skillbelt/browser-pane/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/gw-space/claude-skillbelt/browser-pane"><img src="https://agentmods.dev/badge/skills/gw-space/claude-skillbelt/browser-pane.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 | $0.00095 | $0.00690 |
| Opus 5 | $0.00048 | $0.00345 |
| Sonnet 5 | $0.00019 | $0.00138 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
browser-pane scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
browser-pane
cmux 우측에 단일 브라우저 pane 을 만들어(이미 있으면 재사용) 주어진 URL 을 연다.
로컬 dev 서버·대시보드·문서 사이트 등을 작업 흐름을 끊지 않고 옆에서 볼 때 쓴다.
(마크다운 파일 을 렌더링해 보여주려면 doc-preview-pane 을 쓴다 — 이 스킬은 URL 용.)
When to use
- 사용자가 "이 URL/사이트/서버 오른쪽에 띄워줘 / 보여줘" 라고 할 때.
- 로컬 dev 서버나 미리보기 서버를 띄운 직후 — 바로 옆 pane 에서 확인하게 한다.
How to use
URL 하나 이상을 헬퍼 스크립트에 넘긴다:
bash "${CLAUDE_PLUGIN_ROOT}/skills/browser-pane/scripts/open-url.sh" <url> [<url> ...]
예:
# 로컬 서버
bash "${CLAUDE_PLUGIN_ROOT}/skills/browser-pane/scripts/open-url.sh" http://127.0.0.1:8000
# scheme 생략 가능 (http:// 자동)
bash "${CLAUDE_PLUGIN_ROOT}/skills/browser-pane/scripts/open-url.sh" localhost:3000
# 여러 개 → 같은 pane 에 탭으로
bash "${CLAUDE_PLUGIN_ROOT}/skills/browser-pane/scripts/open-url.sh" localhost:3000 https://example.com
- scheme 없는 인자에는
http://가 자동으로 붙는다. - 포커스는 현재 (agent) pane 에 유지된다 — 입력 흐름이 끊기지 않는다.
Behavior & guarantees
- 단일 pane 재사용: workspace 별로 브라우저 pane UUID 를
~/.local/state/cmux-browser-pane/<workspace-id>.pane에 저장. 다음 호출 때 살아있으면 재사용(탭 추가), 닫혔으면 새로 우측 split. → 호출할수록 화면이 쪼개지지 않음. - Best-effort: cmux 가 없거나(다른 터미널), workspace 밖이거나, pane 생성/open 실패해도
exit 0으로 조용히 빠진다. 본 작업에는 영향 없음. - agent pane 안전: 항상 전용 우측 pane 에만 열고, 현재 작업 중인 pane 에는 절대 열지 않는다.
- 브라우저 기능이 꺼져 있으면
cmux enable-browser로 먼저 켠다.
Notes
- 우측 pane 을 사용자가 닫았다면 다음 호출 때 자동으로 다시 만든다.
- 같은 pane 에 여러 번 열면 탭이 쌓인다 — 필요 없는 탭은 사용자가 닫으면 된다.
What ships with it
2 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.
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.
- 10d ago First seen · 50 lines · 95 tokens per session scan A 27d82a696a9a
browser-pane is a skill published in the GitHub repository gw-space/claude-skillbelt (2 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 690 once invoked, about $0.0005 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.
Other skills, from other repositories
wiki-serve
Start the wiki web server — browsable Wikipedia-style UI with live research, split-pane editor, AI assist, and themes. Manual trigger only: /wiki-serve, 'start wiki server', 'browse the wiki'.
verify-feature
Auto-detect changed frontend routes, navigate them with Playwright, take screenshots, and check for console/network errors. Use after implementing a frontend feature to verify it works visually — auto-detects routes from git changes or accepts a route argument. Supports --responsive for mobile testing and…
screenshot
Capture a screenshot of a URL or route with one command. Use whenever the user wants to take a screenshot, capture a page, see what a route looks like, or visually verify a page. Supports mobile viewport with --mobile and unauthenticated mode with --no-auth.
demo-video
Orchestrates building a narrated demo video of a project — reads the codebase, writes a storyboard, prepares deterministic app state, drives the UI with Playwright to record clips (web and Electron), generates ElevenLabs voiceover, reconciles measured durations into a timeline, and renders the final cut with Remotion.…
demo-capture
Records demo video clips by driving a running app — one clip per storyboard section, with human-feeling pointer motion, dwell timing, and per-character typing. Covers the Playwright MCP video tools for web apps and a generated Playwright Electron script (plus a macOS screen-capture fallback) for desktop apps. Use when…
smoke-test
Smoke test the running frontend and API by navigating key routes with Playwright, checking for console errors and broken pages. Use after starting the dev server or to verify the app works before creating a PR.