David Ondrej's Agent Skills is a repository of reusable instruction packages for AI coding, research, and workflow agents. Each skill describes a focused process for tasks such as code improvement, research, documentation, transcript work, and agent coordination. The catalogue entries are the repository's own skills and related agent configuration.
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 davidondrej/skills --skill google-safe-browsinggit clone --depth 1 https://github.com/davidondrej/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/davidondrej/skills/google-safe-browsing)<a href="https://agentmods.dev/skills/davidondrej/skills/google-safe-browsing"><img src="https://agentmods.dev/badge/skills/davidondrej/skills/google-safe-browsing/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/davidondrej/skills/google-safe-browsing"><img src="https://agentmods.dev/badge/skills/davidondrej/skills/google-safe-browsing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high YARA Match · line 20 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00105 | $0.01014 |
| Opus 5 | $0.00053 | $0.00507 |
| Sonnet 5 | $0.00021 | $0.00203 |
| Haiku 4.5 | $0.00011 | $0.00101 |
Grade A, and why
google-safe-browsing 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.
curl -s "https://transparencyreport.google.com/transparencyreport/api/v3/safebrowsing/status?site=example.com" How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Safe Browsing: Prevent and Fix
One upstream blocklist (Google Safe Browsing) feeds Chrome, Brave, Safari, Firefox, and Edge. A flag there blocks the site in every browser at once. It is a classification of the public surface, not a hack — do not start by debugging code.
Quick check: is a site flagged?
# Replace the domain. Check apex AND www — they are scored separately.
curl -s "https://transparencyreport.google.com/transparencyreport/api/v3/safebrowsing/status?site=example.com"
Response is )]}' followed by [["sb.ssr", STATUS, bool, bool, bool, bool, bool, timestamp_ms, "site"]]:
STATUS 1+ allfalse= clean.STATUS 2+ anytrue= flagged. The browser interstitial text tells the category: "trick you into revealing passwords" = deceptive/social-engineering; "install dangerous programs" = malware.
Human-readable version: https://transparencyreport.google.com/safe-browsing/search?url=example.com
Prevention checklist (every new public web project)
- No third-party trademarks in the domain.
youtube-x.com,paypal-tool.io= brand + login form = automated phishing flag, and a trademark complaint risk. Use subdomains of a domain you own (tool.yourname.com). - Crawlers must never land on a credential form. Root URL for anonymous visitors goes to a neutral landing page: no inputs, clear owner ("Operated by X"), explicit "Not affiliated with [brand]" if the product touches one. Login lives behind a link.
- Search Console on day one, every domain. Add a Domain property, drop the TXT record at the registrar. It is the only channel where Google warns you BEFORE users see red screens, and the only door to request a review after a flag.
- Public URL = public site. "Internal tool" means nothing to a classifier. Kill stray waitlist/signup forms on tools that are actually invite-only; young domain + email-collection forms looks like a harvesting kit.
- Verify like a stranger.
curl -sL https://the-domain/and check: lands on neutral content, no password field, no third-party brand in title/headings.
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 Changed 035e7a4cc4a6
- 9d ago First seen · 50 lines · 105 tokens per session scan A a6f84703acb3
google-safe-browsing is a skill published in the GitHub repository davidondrej/skills (3,989 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 1,014 once invoked, about $0.0005 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
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.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.