runtime

runtime is a command for coding agents from yurilopes/pydoll-mcp-server. It costs 0 tokens per session (575 once invoked), scanned A, original, MIT.

A set of commands for running JavaScript inside a web browser and managing the browser's runtime state.

In plain words
What is it for?
It helps execute expressions, call functions on page objects, compile scripts, run them later, and inspect object properties.
Why use it?
It lets code inspect or change a page using JavaScript while the browser is running.

Command

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 commands/yurilopes/pydoll-mcp-server/runtime
Clone the repo
git clone --depth 1 https://github.com/yurilopes/pydoll-mcp-server

Wrote 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.

agentmods badge for runtime

README.md
[![agentmods](https://agentmods.dev/badge/commands/yurilopes/pydoll-mcp-server/runtime.svg)](https://agentmods.dev/commands/yurilopes/pydoll-mcp-server/runtime)
Your own site
<a href="https://agentmods.dev/commands/yurilopes/pydoll-mcp-server/runtime"><img src="https://agentmods.dev/badge/commands/yurilopes/pydoll-mcp-server/runtime.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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 $0.00000 $0.00575
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 3d ago against content hash 0b0b63b39fb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime 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 3d 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.

references/pydoll-docs/en/api/commands/runtime.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runtime Commands

Runtime commands provide JavaScript execution capabilities and runtime environment management.

Overview

The runtime commands module enables JavaScript code execution, object inspection, and runtime environment control within browser contexts.

::: pydoll.commands.runtime_commands options: show_root_heading: true show_source: false heading_level: 2 filters: - "!^_" - "!^__"

Usage

Runtime commands are used for JavaScript execution and runtime management:

from pydoll.commands.runtime_commands import evaluate, enable
from pydoll.connection.connection_handler import ConnectionHandler

# Enable runtime events
connection = ConnectionHandler()
await enable(connection)

# Execute JavaScript
result = await evaluate(
    connection, 
    expression="document.title",
    return_by_value=True
)
print(result.value)  # Page title

Key Functionality

The runtime commands module provides functions for:

JavaScript Execution

  • evaluate() - Execute JavaScript expressions
  • call_function_on() - Call functions on objects
  • compile_script() - Compile JavaScript for reuse
  • run_script() - Run compiled scripts

Object Management

  • get_properties() - Get object properties
  • release_object() - Release object references
  • release_object_group() - Release object groups

Runtime Control

  • enable() / disable() - Enable/disable runtime events
  • discard_console_entries() - Clear console entries
  • set_custom_object_formatter_enabled() - Enable custom formatters

Exception Handling

  • set_async_call_stack_depth() - Set call stack depth
  • Exception capture and reporting
  • Error object inspection

Advanced Usage

Complex JavaScript Execution

# Execute complex JavaScript with error handling
script = """
try {
    const elements = document.querySelectorAll('.item');
    return Array.from(elements).map(el => ({
        text: el.textContent,
        href: el.href
    }));
} catch (error) {
    return { error: error.message };
}
"""

result = await evaluate(
    connection,
    expression=script,
    return_by_value=True,
    await_promise=True
)

Read the full file on GitHub · 110 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. 3d ago First seen · 110 lines · 0 tokens per session scan A 0b0b63b39fb6

Subscribe to this mod's changes

runtime is a command published in the GitHub repository yurilopes/pydoll-mcp-server (1 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 575 tokens. 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.