DAILY DROP · NOV 11, 2026

Today's drop: 1 new tool, 4 listing updates

The directory now lists 150 hand-checked tools. New today: Modern Web Guidance, a free open-source agent skill and CLI from the Chrome, Edge, Firefox and MDN teams that steers your coding agent toward modern web APIs instead of old JavaScript patterns. Updated: GitHub Copilot and Gemini (Gemini 4 Carbon), Cursor (multiplayer Projects) and Stroq (v0.32). Coding & Vibe Coding grows to 26 tools and AI for IT & Cybersecurity stays at 60. Pricing only where the official page states it.

Previous drop: Nov 10, 2026 →

Get the weekly dropThe best new AI tools, one email a week. Free.

New in the directory 1

Browse all 150
Tool
Category
Price
Status
Link
Modern Web GuidanceFree, open-source (Apache-2.0) agent skill and CLI that feeds your coding agent current web-platform best practices so it stops writing 2019-style JavaScript: native dialogs and popovers, CSS anchor positioning, container queries, view transitions, field-sizing, INP performance fixes, accessibility patterns, passkeys and Chrome's built-in AI APIs, each with browser-compatibility guidance and lightweight fallbacks. Stewarded by the Google Chrome, Microsoft Edge, Mozilla Firefox and MDN teams. Install with npx modern-web-guidance@latest install (or npx skills add / gh skill install GoogleChrome/modern-web-guidance); it works with any coding agent that supports skills (Claude Code, Codex, Gemini CLI, Copilot and others). The CLI searches 200+ expert-reviewed guides offline (no API keys, no network calls for search), and the new legacy-scan command looks through your code for old patterns your agent can modernize. The Chrome team reports agents passing 92% of its 200-task eval with the skill versus 55% without (the team's own eval). The Show HN post runs its commands with DISABLE_TELEMETRY=1, so set that if you don't want usage telemetry. The 1.0 stable release was announced Nov 10, 2026 (preview since Google I/O in May); about 3,770 GitHub stars and a Show HN near 380 points.
Price Free and open source (Apache-2.0)
FREE TIERchecked 11/11

Why this one

  • Modern Web Guidance fixes a habit every vibe coder has seen: ask an agent for a modal, tooltip or auto-growing textarea and it writes 50 lines of JavaScript or pulls in a library, when the browser already has <dialog>, the Popover API, anchor positioning or field-sizing. It is a free, open-source (Apache-2.0) skill plus a small CLI, stewarded by the Google Chrome, Microsoft Edge, Mozilla Firefox and MDN teams. Run npx modern-web-guidance@latest install and your agent (Claude Code, Codex, Gemini CLI, Copilot or any agent that supports skills) can search 200+ expert-reviewed guides offline and pull only the one it needs into context. The new legacy-scan command lists old patterns in your code that the agent can modernize. The Chrome team reports agents passing 92% of its 200-task eval with the skill versus 55% without; that is the team's own eval. Version 1.0 was announced Nov 10 after a preview since May, with about 3,770 GitHub stars and a Show HN near 380 points. The Show HN commands set DISABLE_TELEMETRY=1, so do the same if you don't want usage telemetry. For IT learners it is also a quick way to see what modern, accessible front-end code looks like before you build a portfolio site.

Listing updates

Checked on Nov 11, 2026 against official pages and release notes.

  • GitHub Copilot: Google's Gemini 4 Carbon is generally available in Copilot (Nov 10) for Pro+, Max, Business and Enterprise users, billed at provider list pricing under usage-based billing, in VS Code, Visual Studio, JetBrains, Xcode, Eclipse, Copilot CLI, the coding agent, the Copilot app, github.com and GitHub Mobile. Rollout is gradual, and Business and Enterprise admins control it through the model policy.
  • Gemini: Gemini 4 Carbon (Nov 10) is what Google calls its strongest model for long-running agent work and cybersecurity. Developers can use it on the paid tier of the Gemini API in Google AI Studio and Android Studio; Google AI Ultra subscribers can try it in AI Studio and in Google Antigravity.
  • Cursor: Projects, the workspace where one coordinator directs a fleet of agents, is now multiplayer (beta, rolling out to all users Nov 10). Teammates share requirements docs, specs and mockups as context every agent can read, a shared task board shows who and which agent is on each task with its PR, and teammates' coordinators can plan around each other's work.
  • Stroq: v0.32.0 (Nov 11) reads Cursor sessions on its card alongside Claude Code and Codex (read-only), and lets you mark a flagged moment as a false alarm with stroq show --false-alarm from a terminal; the mark is dropped if the evidence changes, and Stroq's hook refuses marks made through an agent's shell.

Category changes

Checked, not listed

  • agentaudit (Manifold Security, Nov 10): a free open-source (Apache-2.0) CLI that reads a repo's .claude/, .cursor/ and .codex/ config and lists hooks, MCP servers and credential helpers before you open it. Useful idea, but about a dozen GitHub stars so far, so it waits.
  • Vaikora Guard MCP (Data443) and airgap-check (Humanet): new open-source agent-policy and offline-readiness tools; too early to show traction.
  • Runpod for Agents: Runpod's MCP server and skills for GPU infrastructure; outside our IT and coding focus for most readers.
  • Strix v1.7.1, Orca v1.4.256, OpenCode v2.2.7, Hermes Agent v0.23.1 and 0 v0.28.10: routine releases, no listing change. Ollama v0.40.17 is still a release candidate.