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 siarhei-belavus/agent-public --skill agent-browsergit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/agent-browser)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/agent-browser"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/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/siarhei-belavus/agent-public/agent-browser"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/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 | $0.00108 | $0.04930 |
| Opus 5.5 | $0.00043 | $0.01972 |
| Sonnet 5.5 | $0.00022 | $0.00986 |
| Haiku 4.5 | $0.00011 | $0.00493 |
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 2mo 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.
This is a copy
83% identical to agent-browser — 209 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
Version: targets agent-browser >= 0.15.0 (tested 0.15.2). If your installed agent-browser --version is older, run via npx -y [email protected] ... or upgrade.
Sessions:
--session <name>= isolated in-memory browser context (parallel work)--session-name <name>= auto-save/restore state (cookies/storage) across restarts- Combine both if needed:
agent-browser --session <run> --session-name <persist> ...
Login wall handling (choose method)
If you hit a login wall (SSO/2FA/CAPTCHA, forced redirect to /login, auth modal, etc.), pause and ask the user which login method they want (use the ask_user tool; do not ask for passwords in chat).
Options:
- Manual (headed) login (recommended for SSO/2FA/CAPTCHA)
- Auth profile (automated) login (built-in
agent-browser auth, for simple username/password flows)
After login (either method): persist the authenticated session/state and then resume the original user goal.
Path A — Manual (headed) login
-
Open headed + isolate session (so auth can be reused):
agent-browser --headed --session-name <site> open <login-url> -
Ask user to complete login in the visible browser window.
-
Persist the session (pick one):
-
Auto (recommended):
agent-browser close # auto-saves state for --session-name <site> -
Explicit file (portable):
agent-browser state save <site>-auth.json
-
-
Proceed with original goal using the same saved session/state:
agent-browser --session-name <site> open <target-url> # or: agent-browser state load <site>-auth.json && agent-browser open <target-url>
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 5.6 KB
- references/commands.md 6.7 KB
- references/profiling.md 3.3 KB
- references/proxy-support.md 4.9 KB
- references/session-management.md 4.7 KB
- references/snapshot-refs.md 4.2 KB
- references/video-recording.md 3.5 KB
- templates/authenticated-session.sh 3.6 KB runs code
- templates/capture-workflow.sh 1.8 KB runs code
- templates/form-automation.sh 1.8 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.
- 2mo ago First seen · 577 lines · 108 tokens per session scan A 36af26e36f71
agent-browser is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 5mo ago), licensed MIT. It adds 108 tokens to every session and 4,930 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to agent-browser, differing in 209 lines, and is treated as a copy.
Other skills, from other repositories
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…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.