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 pioneerdotai/pioneer --skill browsergit clone --depth 1 https://github.com/pioneerdotai/pioneerWrote 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/pioneerdotai/pioneer/browser)<a href="https://agentmods.dev/skills/pioneerdotai/pioneer/browser"><img src="https://agentmods.dev/badge/skills/pioneerdotai/pioneer/browser/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/pioneerdotai/pioneer/browser"><img src="https://agentmods.dev/badge/skills/pioneerdotai/pioneer/browser.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 | $0.00026 | $0.03107 |
| Opus 5 | $0.00013 | $0.01554 |
| Sonnet 5 | $0.00005 | $0.00621 |
| Haiku 4.5 | $0.00003 | $0.00311 |
Grade D, and why
browser scanned grade D with 3 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo tee /etc/apparmor.d/agent-browser-chrome >/dev/null <<'EOF' Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.4/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.4/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Installation
For normal browser work, run the requested agent-browser ... command directly. Do not run setup checks before every browser action.
Run setup only when provisioning the skill, when agent-browser is missing, or when browser dependencies need repair. If Node.js and npm are already installed, do not reinstall or replace them. Use the OS-specific Node.js install block only when node or npm is missing, then install agent-browser.
macOS and Linux
# Download and install nvm:
if ! command -v node >/dev/null 2>&1 || ! command -v npm >/dev/null 2>&1; then
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.4/install.sh | bash
# In lieu of restarting the shell:
\. "$HOME/.nvm/nvm.sh"
# Download and install Node.js:
nvm install 24
fi
# Verify the Node.js version:
node -v # Should print the active Node.js version.
# Verify npm version:
npm -v # Should print the active npm version.
Windows
# Download and install Chocolatey:
if (-not (Get-Command node -ErrorAction SilentlyContinue) -or -not (Get-Command npm -ErrorAction SilentlyContinue)) {
if (-not (Get-Command choco -ErrorAction SilentlyContinue)) {
powershell -c "irm https://community.chocolatey.org/install.ps1|iex"
}
# Download and install Node.js:
choco install nodejs --version="24.16.0" -y
}
# Verify the Node.js version:
node -v # Should print the active Node.js version.
# Verify npm version:
npm -v # Should print the active npm version.
Install agent-browser
npm install -g agent-browser
agent-browser install
agent-browser install --with-deps
From Source
git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install
Quick start
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
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.
- 9d ago First seen · 429 lines · 26 tokens per session scan D 34b83c3b9700
browser is a skill published in the GitHub repository pioneerdotai/pioneer (11 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 3,107 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
search-craft
How to get real coverage out of a search engine that returns a handful of results per query, and when to reach for the crawler or the browser instead. Use at the start of any search that has to be thorough rather than quick.
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ha-data-analytics
A local-first data-analysis and reporting skill for CSV and spreadsheet files. It produces decision-ready analyses and shareable offline reports while separating facts, calculations, interpretations, and recommendations.