20 boosters for "safety" — open source, verified from GitHub, ready to install
"name": "claude-obsidian", "description": "Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 \"Compound Vault\" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment wit
If a concern is not "X calls a lock/alloc/ObjC from a signal-reachable path" or "a comment misstates signal safety", it does not belong in the output. When in doubt, cut it. The authoritative rules live in . Read that file before every review — do not summarize or duplicate the rules here; they may
"name": "safety-net", "description": "Block destructive git and filesystem commands before execution", "email": "jliew@420024lab.com"
"description": "Agent orchestration harness for Claude Code — campaign persistence, fleet coordination, intent routing", "name": "SethGammon" "homepage": "https://github.com/SethGammon/Citadel",
Procedural memory for AI coding agents. Transforms scattered sessions into persistent, cross-agent memory. Uses a three-layer cognitive architecture that mirrors human expertise development. AI coding agents accumulate valuable knowledge but it's: You've solved auth bugs three times this month acros
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs --> If is , do not proactively suggest ostack skills — only invoke
"name": "claude-harness", "description": "Long-running agent harness with 5-layer memory architecture, GitHub integration, autonomous batch processing, Agent Teams with ATDD, 9 hooks (safety, quality gates, team coordination), and 6 Agent Skills", "name": "panayiotis"
This project includes deepsafe-scan, a preflight security scanner for AI agent environments. When the user asks to audit, scan, or check security of their AI agent setup, skills, or MCP servers, run the scanner: For a full scan with LLM analysis (if OPENAIAPIKEY is set):
"description": "Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 23 hook scripts, auto-learning pipeline, hook profiles, and multi-language coding standards", "name": "xiaobei930", "url": "https:
"name": "project-boundary", "description": "Blocks destructive commands outside the project directory. Allows file operations within the project (refactoring, cleanup) but prevents accidental damage outside it.", "name": "Justyna Wojtczak",
"name": "ultraship", "description": "Claude Code plugin — 36 tools, 42 skills, 12 agents. Elite SEO strategy with AI traffic tracking, IndexNow, GSC-GA4 cross-reference, CTR anomalies, brand filtering, keyword intelligence, index doctor, pentest, ship, launch, grow, rescue.", "name": "Houseofmvps",
"description": "Smart command safety filter for Claude Code — parses shell pipelines and evaluates per-command safety rules to auto-approve safe commands and block dangerous ones",
"name": "laravel-api", "name": "Steve King", "email": "steve@juststeveking.com"
"name": "medical-mcps", "version": "0.1.17", "description": "Comprehensive biological and medical research data integration server providing unified access to 13+ specialized databases including Reactome (pathways), KEGG (pathways/diseases), UniProt (proteins), ChEMBL (drug discovery), PubMed (liter
A Korean-language code review guide for the Trade Safety project, providing development standards for a K-pop merchandise trading safety analysis tool. Developers building scam-detection features for international fan communities would benefit from its architectural and code quality guidelines.
cpp-pro is a C++ expert agent that helps developers write modern, idiomatic C++ code with RAII, smart pointers, templates, and performance optimization. It's essential for teams refactoring legacy C++ or building memory-safe, high-performance applications.
SafeRun provides automatic safety guardrails for AI agents by classifying shell commands as BLOCK, ASK, or ALLOW before execution, preventing dangerous operations like force pushes and recursive deletes. Developers and AI systems that execute shell commands benefit from this protection without needing manual configuration.
A skill for safely monitoring and controlling Klipper/Moonraker 3D printers through the Moonraker API with built-in confirmation protocols. Useful for developers and makers integrating 3D printer automation into AI-powered workflows.
A Copilot prompt for K-pop fans to detect scams and stay safe when trading merchandise, combining development best practices with fandom community protection.
