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/danielmiessler/lifeos/brightdatanpx skills add danielmiessler/LifeOS --skill brightdatagit clone --depth 1 https://github.com/danielmiessler/LifeOSWhat 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 | $0.00133 | $0.01147 |
| Opus 5 | $0.00067 | $0.00574 |
| Sonnet 5 | $0.00027 | $0.00229 |
| Haiku 4.5 | $0.00013 | $0.00115 |
Grade A, and why
BrightData 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 2d 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.
description: "4-tier progressive web scraping that auto-escalates WebFetch to curl to Interceptor to Bright Data proxy for bot detection and CAPTCHAs, with single-URL and multi-page crawl modes, output as markdown. USE W How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customization
Before executing, check for user customizations at:
~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/BrightData/
If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.
🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)
You MUST send this notification BEFORE doing anything else when this skill is invoked.
-
Send voice notification:
curl -s -X POST http://localhost:31337/notify \ -H "Content-Type: application/json" \ -d '{"message": "Running the WORKFLOWNAME workflow in the BrightData skill to ACTION"}' \ > /dev/null 2>&1 & -
Output text notification:
Running the **WorkflowName** workflow in the **BrightData** skill to ACTION...
This is not optional. Execute this curl command immediately upon skill invocation.
BrightData
Scrapes a single URL (FourTierScrape) or crawls a whole site (Crawl), escalating through four tiers only as far as each page needs. Output is always markdown. Start at Tier 1 and step up only when blocked — reaching for the heavy proxy every time wastes Tier-4 credits. A Cloudflare Accept: text/markdown pre-check runs before Tier 1 (recipe in FourTierScrape.md).
The four tiers (tool contract)
| Tier | Tool | Wins on | Cost / latency |
|---|---|---|---|
| 1 | WebFetch | public content, no bot detection | free · ~2-5s |
| 2 | curl + Chrome headers | user-agent / basic header checks | free · ~3-7s |
| 3 | Interceptor (real Chrome) | JavaScript-rendered / SPA pages | free · ~10-20s |
| 4 | Bright Data MCP mcp__Brightdata__scrape_as_markdown |
CAPTCHA, advanced fingerprinting, residential-IP needs | Bright Data credits · ~5-15s |
Playwright is banned across LifeOS — Tier 3 is Interceptor. Skip-ahead: explicit "use Bright Data" → Tier 4; "use browser" → Tier 3; a domain that already failed Tier 1 → start at Tier 2. The exact curl header block, Cloudflare pre-check, and Interceptor commands live in Workflows/FourTierScrape.md.
What ships with it
2 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.
- 2d ago First seen · 76 lines · 133 tokens per session scan A a2e2cfc8fb24
BrightData is a skill published in the GitHub repository danielmiessler/LifeOS (18,798 stars, last pushed 18d ago), licensed MIT. It adds 133 tokens to every session and 1,147 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
browser-spa-framework
Architecture/conventions for the Echo browser SPA: Go stdlib server :3740, Vite-built TS+JS SPA (embedded web/dist), JSON envelope, WebSocket hub, chat tool loop, shared appdata echo.json, internal/tools registry, tool-generated media transport (Phase 0/1), and the file-browser image/video/audio preview surface…
global-notifications
How Echo surfaces cross-surface/cross-tab alerts to the user: global WebSocket broadcasts (chatcompleted, planquestionsawaiting) mirrored by frontend notification modules that play sounds, show OS/browser Notifications, and deep-link on click.
browse
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. 100ms per command. Use when you need to test a…
pair-agent
Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on…
frontend-excellence
Modern frontend patterns for React Server Components, performance optimization, and Core Web Vitals.