BrowserAct is a browser automation system that lets AI agents use real, separate browser sessions to extract data and complete account-based web tasks. It is for agents and teams that need parallel workflows, reused login states, human handoffs, or access to sites that resist ordinary automated requests.
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/browser-act/skills/google-news-api-skillnpx skills add browser-act/skills --skill google-news-api-skillgit clone --depth 1 https://github.com/browser-act/skillsWrote 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/browser-act/skills/google-news-api-skill)<a href="https://agentmods.dev/skills/browser-act/skills/google-news-api-skill"><img src="https://agentmods.dev/badge/skills/browser-act/skills/google-news-api-skill.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 5.1 | $0.00109 | $0.01312 |
| Opus 5 | $0.00055 | $0.00656 |
| Sonnet 5 | $0.00022 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
google-news-api-skill 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 7d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google News Automation Skill
📖 Introduction
This skill provides a one-stop news collection service using BrowserAct's Google News API template. It directly extracts structured news results from Google News, including headlines, sources, publication times, and article links. Simply input search keywords and time filters to get clean, usable news data.
✨ Features
- No Hallucinations: Pre-set workflows avoid AI generative hallucinations, ensuring stable and precise data extraction.
- No Captcha Issues: No need to handle reCAPTCHA or other verification challenges.
- No IP Restrictions: No need to handle regional IP restrictions or geofencing.
- Faster Execution: Tasks execute faster compared to pure AI-driven browser automation solutions.
- Cost-Effective: Significantly lowers data acquisition costs compared to high-token-consuming AI solutions.
🔑 API Key Setup
Before running, check the BROWSERACT_API_KEY environment variable. If not set, do not take other measures; ask and wait for the user to provide it.
Agent must inform the user:
"Since you haven't configured the BrowserAct API Key, please visit the BrowserAct Console to get your Key."
🛠️ Input Parameters
Agent should flexibly configure the following parameters based on user needs:
-
Search_Keywords (Search Keywords)
- Type:
string - Description: The content to search on Google News. Can be company names, industry terms, competitor names, etc.
- Example:
AI Startup,Tesla,SpaceX
- Type:
-
Publish_date (Time Range)
- Type:
string - Description: Filter news by publication time.
- Options:
any time: No restrictionpast hours: Past few hours (breaking news)past 24 hours: Past 24 hours (daily monitoring)past week: Past week (short-term trends)past year: Past year (long-term research)
- Default:
past week
- Type:
What ships with it
1 file 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.
- 7d ago First seen · 93 lines · 109 tokens per session scan A 2b7625306fcf
google-news-api-skill is a skill published in the GitHub repository browser-act/skills (5,689 stars, last pushed 13d ago), licensed MIT. It adds 109 tokens to every session and 1,312 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
skill-monitor
Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
promote
Generate X/Twitter release promotion posts with ASCII tables and CodeSnap rendering. Use when writing release posts, promotion tweets, plugin announcements, or preparing social media content for new versions.
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.