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 kwannoel/the-controller --skill agent-browsergit clone --depth 1 https://github.com/kwannoel/the-controllerWrote 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/kwannoel/the-controller/agent-browser)<a href="https://agentmods.dev/skills/kwannoel/the-controller/agent-browser"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/agent-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/kwannoel/the-controller/agent-browser"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/agent-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 | $0.00059 | $0.01505 |
| Opus 5.5 | $0.00024 | $0.00602 |
| Sonnet 5 | $0.00012 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
agent-browser 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 yesterday.
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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
agent-browser is the Chromium skill. Prefer it when the user wants the agent to work against the browser they already have open and logged into.
The primary model is OpenClaw-style relay control:
- Open the target site in Chrome or Chromium.
- Attach the browser relay extension to the tab you want the agent to control.
- Run
agent-browsercommands against that attached tab. - Detach when you are done.
If relay mode is unavailable, fall back to a managed dedicated browser profile.
Mode Selection
Relay mode
Use relay mode when:
- the user is already logged in
- the task depends on the user's real browser extensions, cookies, or in-progress state
- the user wants to avoid login churn
Relay mode means the agent controls a real Chrome or Chromium tab. Treat that tab as sensitive. Use the minimum scope needed and avoid unrelated tabs.
Managed mode
Use managed mode when:
- the user wants isolation from their daily browser
- the relay is not installed or not attached
- the task needs a dedicated automation profile
Managed mode launches or reuses a dedicated browser profile instead of the user's live browsing tab.
Core Workflow
Every agent-browser task follows this pattern:
- Confirm the right tab is attached in relay mode, or start managed mode.
- Snapshot the page:
agent-browser snapshot -i - Interact with refs:
click,fill,select,check - Re-snapshot after navigation or major DOM changes
# Attached tab is already open in Chrome/Chromium
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Sign in"
agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i
Do not close the browser in relay mode unless the user explicitly asks for that. In relay mode, prefer detach over agent-browser close.
Quick Start
What ships with it
10 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.
- references/authentication.md 2.6 KB
- references/commands.md 1.4 KB
- references/profiling.md 845 B
- references/proxy-support.md 903 B
- references/session-management.md 1.2 KB
- references/snapshot-refs.md 878 B
- references/video-recording.md 576 B
- templates/authenticated-session.sh 1.0 KB runs code
- templates/capture-workflow.sh 835 B runs code
- templates/form-automation.sh 1.1 KB runs code
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.
- yesterday First seen · 224 lines · 59 tokens per session scan A 2f6d790d8aba
agent-browser is a skill published in the GitHub repository kwannoel/the-controller (13 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 1,505 once invoked, about $0.0002 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 2026-09-23.
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
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
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.