terminal-browser is a web browser that runs inside a terminal window, allowing pages to be viewed and controlled alongside command-line work. It is intended for developers and coding agents that need web access in the same terminal session, including when working over SSH. The catalogue add-ons help agents interact with the browser and use it as part of their workflow.
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 zenbu-labs/terminal-browser --skill verifygit clone --depth 1 https://github.com/zenbu-labs/terminal-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/zenbu-labs/terminal-browser/verify)<a href="https://agentmods.dev/skills/zenbu-labs/terminal-browser/verify"><img src="https://agentmods.dev/badge/skills/zenbu-labs/terminal-browser/verify.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01053 |
| Opus 5 | $0.00018 | $0.00526 |
| Sonnet 5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
verify 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apps here render via the kitty graphics protocol, so they can be verified
without a real terminal. Every verification is recorded: the harness in
tools/verify-recorder/ captures every frame the app emits, overlays your
inputs (click ripples, caption bar), encodes a video, and generates a summary
page. Do not hand-roll one-off pty scripts that only dump PNGs.
Writing a verification
Write a driver script (in /tmp is fine) using the checked-in package:
import sys
sys.path.insert(0, "<repo>/tools/verify-recorder")
from driver import Driver
from recorder import Recorder
rec = Recorder("wheel-pan", title="Wheel pan keeps cursor anchored")
d = Driver(["<repo>/engine/target/debug/typing"], rec,
cols=120, rows=32, xpixel=1200, ypixel=800)
d.pump(3.0) # pump between actions so frames arrive
rec.check("app painted", d.frame_size is not None, f"{d.frame_size}")
w, h = d.frame_size # REAL framebuffer size — always use this
d.text("hello", "type into editor") # every input takes a description
d.click(w // 2, h // 3, "select the note") # mouse coords are pixels (1016 mode)
d.wheel(w // 2, h // 2, down=True, n=3, description="scroll content")
d.pump(1.0)
rec.check("scroll redrew", len(rec.frames) > 40, f"{len(rec.frames)} frames")
rec.still("after-scroll") # named snapshot for the summary page
d.stop("ctrl+c") # or "ctrl+q" depending on the app
rec.finish() # composites markers, encodes mp4, writes summary
Driverspawns the argv in a pty (TERM=xterm-kitty, TIOCSWINSZ with pixel dims, answers the\x1b[?1016$pmouse probe), decodes kittya=T,f=32,o=zframes, and feeds them to the recorder. Node apps: spawn["npx", "tsx", "src/main.tsx", ...]withcwd=the package dir (tsx resolves tsconfig from cwd; a wrong cwd silently drops jsx config).- Input methods:
key("enter"/"esc"/"ctrl+q"/"super+shift+z"),text,click,press/drag/release(a drag needs all three —clicksends press+release together),move,wheel. Descriptions become the video caption bar and the summary timeline — write what the step is testing. rec.check(name, ok, detail)for every assertion;rec.still(name)to pin the current frame into the summary.- Give checks real assertions (frame deltas, decoded pixel colors via
recorder.png_read(rec.frames[-1]["path"])) — the summary shows pass/fail.
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.
- 8d ago First seen · 84 lines · 37 tokens per session scan A c300f9c8b032
verify is a skill published in the GitHub repository zenbu-labs/terminal-browser (2,759 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,053 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
web-scrape
Extract structured data from web pages using CSS selectors. Use when the user asks to scrape a website, extract text or links from a page, parse HTML content, get data from a table, read article content, collect image URLs, or pull structured information from any web page. Keywords: scrape, extract, parse, crawl, get…
browser
Browser automation via Playwright MCP — navigate pages, click elements, fill forms, take screenshots, extract text, manage tabs, and run JavaScript in the browser. Use when the user asks to open a website, interact with a web page, scrape dynamic content, fill out forms, take a page screenshot, test a web application…
core-agent-browser
Internal support skill for agent-browser CLI workflows used by rust-learner, docs-researcher, and crate-researcher. Use only when browser automation is explicitly required.
computer-use
OS/window-level inspection and input in visible local app windows through orca computer: native apps, external browser windows (Chrome, Edge, Safari), and app webviews. Not for Orca's embedded browser (use orca-cli) or page-only automation (use Playwright or CDP).
computer-use
Full desktop control on macOS, Windows, Linux, and HarmonyOS — accessibility-first observation and actions with pixel fallback, screenshots, zoom, screen recording, and switching between registered computers as a default.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.