OSSvxcontrol/pentagi — Autonomous AI Pentest Platform (+875 today)GitHub·high signalFully autonomous AI penetration testing with multi-agent delegation, Neo4j knowledge graph, 20+ security tools, Docker sandbox. 4K stars surging +875 today after Claude Code Security launch.SourceSource pageGitHub↳ Follow the threadPolicy dependency / Stack layerponytail: A 'Laziest Senior Dev' Skill That Cuts Agent-Written Code by ~54% Is the Fastest-Rising Repo on GitHubGitHubStack layer / Threat patternsickn33/agentic-awesome-skills Hits 1,900+ Installable Agent Skills — and an Installer CLI to MatchGitHubStack layer / Threat patternClaude Code v2.1.205 Blocks Auto-Mode Transcript Tampering and Prompts Before rm -rf on Unresolved VariablesClaude Code ChangelogStack layer / Threat patternbrowser-use Ships 'Browser Harness' — Agents Edit Their Own Browser Helpers Mid-Task Instead of FailingGitHubStack layer / Threat patternnocobase Pitches the Anti-Vibe-Coding No-Code Platform: AI Works On Top of Production Infra, Not From ScratchGitHubStack layer / Threat patternPattern: Agent 'Fleet' Control Surfaces Are ProliferatingGitHubStack layer / Threat patternPattern: Context Selection Is Consolidating Into Its Own Layer Beneath the AgentGitHubPolicy dependency / Stack layerKastra Launches Policy Enforcement for Claude Code, Cursor, and CodexHacker News