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 agentmods add skills/youngjaedev/my-claude-plugins/brightdata-guidenpx skills add YoungjaeDev/my-claude-plugins --skill brightdata-guidegit clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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/youngjaedev/my-claude-plugins/brightdata-guide)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/brightdata-guide"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/brightdata-guide.svg" alt="Measured on agentmods" 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 | $0.00168 | $0.05358 |
| Opus 5 | $0.00084 | $0.02679 |
| Sonnet 5 | $0.00034 | $0.01072 |
| Haiku 4.5 | $0.00017 | $0.00536 |
Grade A, and why
brightdata-guide scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> Adapted from Bright Data's official MCP and CLI skills (MIT). Security-patched and made agent-agnostic by Dante Labs: removed instructions that autonomously edit host settings files, removed shell-piped installers (cur How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bright Data — MCP & CLI Usage Guide
Adapted from Bright Data's official MCP and CLI skills (MIT). Security-patched and made agent-agnostic by Dante Labs: removed instructions that autonomously edit host settings files, removed shell-piped installers (curl-to-bash) and global
npm -ginstalls (the CLI is installed once by the operator out of band, or run via pinnednpx), and generalized agent/tool naming so it works for any agent.
Runtime tool names — this guide uses generic tool names. Map to your runtime:
terminal-> Bash (Claude) / execute_command (Codex);delegate_task-> the parent's subagent/Task tool. The Bright Data MCP tool names (search_engine,scrape_as_markdown,web_data_*,scraping_browser_*) are identical across Claude and Codex.
Two ways to reach Bright Data — pick by what's in your tool registry
Both paths hit the same Bright Data platform and the same 5,000 free requests/month. Same data, different door.
- MCP tools present (
search_engine,scrape_as_markdown,web_data_*…): call them directly. Follow the MCP sections below. - MCP tools absent — the common case is being a
delegate_tasksubagent: a subagent inherits the parent's terminal and skills but NOT its MCP toolsets, sosearch_engineetc. will not be in your registry. In that case use the Bright Data CLI from the terminal (bdata/brightdata). Jump to "Bright Data CLI (terminal)" andreferences/cli-commands.md.
How to tell which you have: look at your available tools. If you see search_engine/scrape_as_markdown, use MCP. If you only see terminal (no Bright Data tools), use the CLI via terminal. Do not fall back to the agent's built-in web search.
Preflight — four gates, in order, before the first Bright Data call
Bright Data is a primary search and fetch path, not a garnish, so an unconfigured setup must stop and surface the setup step instead of quietly falling back to the agent's built-in web search. Gate 1 is a fork, not a hurdle: when the MCP tools ARE present you are already done — call them (Part A) and skip gates 2-4 entirely, since those check only the CLI path. Gates 2-4 run only when gate 1 finds no MCP tools (the delegate_task subagent case), and there you run them in order and stop at the first that fails. An MCP-only session with no CLI installed is fully configured — it must never be stopped at gate 2.
What ships with it
3 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.
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.
- 4d ago First seen · 343 lines · 168 tokens per session scan A 84f6473f24b0
brightdata-guide is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 168 tokens to every session and 5,358 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
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.
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.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…