@DanKornas highlighted HOL Guard, an open-source local-first security layer that reviews shell commands, file access, package ops, and MCP tool calls before they run—allow, block, or approve by policy. Integrates Codex, Claude Code, Copilot CLI, Cursor, Gemini CLI, and more. Apache 2.0.
Apply to your dev workflow or calculate costs
TestingCatalog (@testingcatalog) reports Showly now lets users connect coding agents and turn agent-built pages into shareable links, with a private preview before public crawlable publish. It works with Claude Code, Codex, Cursor, OpenClaw, Hermes, and other MCP-compatible agents, and publishing requires human permission. Version history, deployment logs, and an agent activity log are included; the free plan offers 300 credits/month, unlimited live sites and custom domains, plus simple rollbacks.
@TiagerBao covered Cloudflare's open-source security-audit-skill (MIT) for coding agents: a six-phase flow that maps architecture and trust boundaries, assigns independent checkers, adversarially disproves candidates, emits findings.json, re-validates, and reports—labeling results confirmed, needs_validation, or rejected. Repo: github.com/cloudflare/security-audit-skill; works with Claude Code, Cursor, and Codex.
CCXT launched the official ccxt-mcp MCP server so AI agents can reach 100+ crypto exchanges and prediction markets—read markets, check balances, and place trades. It works with Claude Code, Codex, Gemini CLI, Cursor, and any MCP client. One-line npx install; market data needs no keys; trading is off by default; OSS at github.com/ccxt/ccxt.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.