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 strikersam/autonomous-ai-agency --skill browserbase-browsergit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/browserbase-browser)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/browserbase-browser"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/browserbase-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/strikersam/autonomous-ai-agency/browserbase-browser"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/browserbase-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 44 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00050 | $0.00839 |
| Opus 5 | $0.00025 | $0.00419 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
browserbase-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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: browserbase-browser — Real Browser Automation
Setup
npm install -g browse # Install the CLI
export BROWSERBASE_API_KEY="bb_live_..." # Get from https://browserbase.com/dashboard
Mode selection
| Situation | Flag | Notes |
|---|---|---|
| Local dev / no bot detection | --local |
Requires Chrome running locally |
| Cloudflare / CAPTCHA / IP limits | --remote |
Uses Browserbase cloud (needs API key) |
| Reuse existing local Chrome session | --auto-connect |
Picks up saved cookies/auth |
Core commands
browse open <url> [--local|--remote] # Navigate — always start here
browse snapshot # Accessibility tree with element refs (fast, low-token)
browse screenshot # Visual capture → .context/screenshots/
browse click "@e5" # Click element ref from snapshot
browse fill "@e3" "value" # Fill input
browse type "text" # Type at cursor
browse press "Enter" # Key press
browse scroll down 3 # Scroll
browse stop # End session
Workflow pattern
# 1. Open — always with explicit mode flag
browse open "https://target.com" --remote # remote for Cloudflare-protected sites
# 2. Snapshot to understand page state (NOT screenshot — 50× fewer tokens)
browse snapshot
# 3. Interact using @ref from snapshot output
browse fill "@e4" "[email protected]"
browse fill "@e5" "password"
browse click "@e6" # Submit button
# 4. Snapshot again to verify state changed
browse snapshot
# 5. Screenshot only when you need visual evidence
browse screenshot
# 6. Always stop when done
browse stop
Applying to local-llm-server platform
# Set env vars first
export BROWSERBASE_API_KEY="your-key"
export PLATFORM_URL="https://local-llm-server.strikersam.workers.dev"
# Login as admin
browse open "$PLATFORM_URL/login" --remote
browse snapshot
# Find email/password fields in snapshot, then:
browse fill "@eN" "[email protected]"
browse fill "@eN" "YOUR_PASSWORD"
browse click "@eN" # Login button
browse snapshot # Confirm: dashboard visible
# Navigate to Agents screen
browse click "@eN" # Agents nav item
browse snapshot
# Navigate to Quick Notes
browse click "@eN" # Quick Notes FAB or nav
browse fill "@eN" "Feature request text here"
browse click "@eN" # Submit
browse stop
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.
- 8d ago First seen · 112 lines · 50 tokens per session scan A acb4505a9224
browserbase-browser is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 839 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 2026-09-03.
Other skills, from other repositories
create-scraper
Given a careers page URL, uses Playwright browser tools to explore the page, identify reliable scraping patterns (preferring hidden JSON APIs over DOM scraping), then writes a TypeScript Scraper subclass for that company.
verify
How to run and drive this app to verify UI/server changes at runtime.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
browser-recording
Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…
web-preview
Emit a hidden preview marker so Kiro Crew's right-panel "Browser" tab opens with a Load-preview card for the URL when you start a local web server for the user to preview. Use whenever you start a dev server or static server so the user can see a site/app you're working on (Vite, Next, npm run dev, python -m…