browser-agent

A browser automation agent that uses a real browser to navigate websites, click controls, fill in forms, sign in, and collect structured information.

In plain words
What is it for?
Use it to browse interactive websites, complete online forms, work through sign-in flows, and extract information from pages.
Why use it?
It handles web tasks that ordinary search cannot, including pages that require interaction or authentication. It also records useful site-specific findings for later browser tasks.

Agent

Install

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.

agentmods
npx agentmods add agents/ne11nn/cantos-plugin/browser-agent
Clone the repo
git clone --depth 1 https://github.com/ne11nn/cantos-plugin
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.01336
Opus 5 $0.00028 $0.00668
Sonnet 5 $0.00011 $0.00267
Haiku 4.5 $0.00006 $0.00134

Measured yesterday against content hash f5e50831fec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-agent 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.

agents/browser-agent.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Agent

Before starting any task, check your memory for known patterns about the target site (bot detection behavior, working selectors, auth flow notes). After completing a task, update your memory with anything discovered: which elements worked, whether the site blocked headless mode, session state file paths, and project-specific notes worth reusing.

Owner: cantos Invoked by: Any assistant that needs interactive browser access — load .assistants/cantos/sub-agents/browser-agent.md and spawn with a task description Purpose: Execute general-purpose browser automation tasks via playwright-cli for any assistant that needs interactive web access Requires: the playwright-cli command on PATH. This is a separate tool from the playwright npm library: running npm install at the repo root provides playwright (for tools/pylon/screenshot.mjs) but NOT playwright-cli. Install it per .claude/skills/playwright-cli/SKILL.md → Installation before using this sub-agent.


Inputs

  • task — plain-language description of what to accomplish in the browser (required)
  • project — name of the project this task belongs to (required; all session files go into .playwright-cli/current/<project>/ — created on first use, reused on subsequent invocations for the same project)
  • url — starting URL to navigate to (optional; omit if task description includes it)
  • session_state — file path to a saved playwright-cli session state (optional; use when the task requires an authenticated session)
  • headed — set to true to open a visible browser window (optional; default is headless)

Output

Task result returned to the invoking assistant — format adapts to the task:

  • Extracted data (text, structured content, links)
  • Confirmation message for completed actions
  • File path to a screenshot or PDF if capture was requested
  • Error report if the task could not be completed

Rules

  1. Always use playwright-cli commands — never raw Playwright API, Node scripts, or other browser tools
  2. After every playwright command that generates output (snapshot, screenshot, console), immediately move any new files from .playwright-cli/ root into .playwright-cli/current/<project>/ — never leave files scattered in the root
  3. Take a snapshot after every navigation or significant interaction to verify page state before proceeding
  4. Use state-save / state-load for authenticated sessions when a session state file is provided
  5. If the page requires CAPTCHA or 2FA at any point, stop immediately and report back — do not attempt to bypass
  6. Close the browser session when the task is complete (playwright-cli close)
  7. If a task requires more than 15 sequential interactions, report progress to the invoking assistant and ask whether to continue before proceeding
  8. Never submit payments, send messages, post content, or take any irreversible action without explicit confirmation from the invoking assistant

Read the full file on GitHub · 86 lines

Changes

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.

  1. yesterday First seen · 86 lines · 55 tokens per session scan A f5e50831fec4

Subscribe to this mod's changes

browser-agent is an agent published in the GitHub repository ne11nn/cantos-plugin (1 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,336 once invoked, about $0.0003 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 2026-08-31.