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 glebis/claude-skills --skill browser-mategit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/browser-mate)<a href="https://agentmods.dev/skills/glebis/claude-skills/browser-mate"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/browser-mate/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/glebis/claude-skills/browser-mate"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/browser-mate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00133 | $0.00956 |
| Opus 5.5 | $0.00053 | $0.00382 |
| Sonnet 5.5 | $0.00027 | $0.00191 |
| Haiku 4.5 | $0.00013 | $0.00096 |
Grade A, and why
browser-mate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser-mate
Non-destructive Chrome automation. The problem it solves: to attach a CDP/agent-browser
session, Chrome must run with --remote-debugging-port. The real-browser skill achieves
this by quitting Chrome Beta first, destroying the user's open tabs. browser-mate
instead runs a dedicated debug Chrome instance (its own --user-data-dir + port) that
coexists with the user's main browser — Chrome permits concurrent instances when the
data dirs differ, so no quit is needed.
The one invariant (never violate)
Never quit, pkill, or osascript quit any browser. The skill only ever launches a
new dedicated instance or reuses an existing one. The single stop path sends SIGTERM only
to a process matched by BOTH our dedicated user_data_dir AND our debug port — never the
user's browser.
Usage
# Ensure a profile's debug Chrome is up (launch or reuse); prints the PORT on stdout
PORT=$(python3 scripts/browser.py chatgpt)
# Then drive it with agent-browser (always pass --cdp $PORT). See references/agent-browser.md
SID=$(LC_ALL=C tr -dc 'a-z0-9' < /dev/urandom | head -c 6)
agent-browser --cdp $PORT --session $SID open "https://chatgpt.com/"
agent-browser --cdp $PORT --session $SID snapshot -i
Other subcommands:
python3 scripts/browser.py list # configured profiles
python3 scripts/browser.py status [profile] # up/down
python3 scripts/browser.py stop chatgpt # SIGTERM OUR instance only (graceful)
For the full agent-browser command set (click, fill, upload, screenshot, reliability,
upgrade gotchas), read references/agent-browser.md.
Profiles
Config: ~/.config/browser-mate/profiles.json (auto-created from assets/profiles.example.json
on first run). Each profile:
{ "default": "automation",
"profiles": {
"automation": { "binary": "<chrome binary>", "user_data_dir": "~/.browser-mate/automation", "port": 9222 },
"chatgpt": { "binary": "<chrome binary>", "user_data_dir": "~/.browser-mate/chatgpt", "port": 9223, "default_url": "https://chatgpt.com/" }
} }
What ships with it
3 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.
- 1mo ago First seen · 78 lines · 133 tokens per session scan A a20d8286ab97
browser-mate is a skill published in the GitHub repository glebis/claude-skills (400 stars, last pushed yesterday), licensed MIT. It adds 133 tokens to every session and 956 once invoked, about $0.0005 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 2026-08-30.
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…