OSStech-leads-club agent-skills Hardened Skill Registry 1.5K StarsGitHub·high signalXBlueskyLinkedInCopy linkSecurity-hardened curated skill registry. Blocks suspicious network calls, manual code review of prompts, filesystem isolation, continuous scanning. Counters 13.4% malicious skill rate.SourceSource pageGitHub↳ Follow the threadPolicy dependency / Stack layerCROSS-CATEGORY: Three Independent Agent-Action Gates Shipped in 48 Hours, All Judging the Command Against Stated IntentProduct Hunt, github.com/AGGIB/Stroq and rewarelabs.com (three independent sources; the 72% figure is Reware's own)Stack layer / Contrastuv 0.12.11 now verifies source archives against uv.lock hashes before running their build backendsGitHubStack layer / ContrastA skill that just tells the agent to stop burying the answer took 4,650 stars in one dayGitHub TrendingStack layer / Update threadPattern: git worktrees became table stakes across three agent harnesses in four daysGitHubStack layer / Update threadKilo Code v7.6.0 adds /goal, a session goal mode that survives failures and pauses on its ownGitHubStack layer / Threat pattern16% of 3,171 public agent-harness setups carry a confirmed security defect, and 3.8% ship a skill that pre-approves your shellarXivStack layergentle-ai carries 919 open items, the largest backlog on today's boards, at 6,583 starsGitHub TrendingStack layerAgentic Stack builds one local knowledge graph across Claude Code, Codex, OpenCode and Cursor historyGitHub