npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

agentic-vault

v1.8.0

Published

A curated collection of high-performance AI skills and system prompts designed for LLMs (Claude, GPT-4o, Gemini). These aren't just "prompts"—they are structurally sound **AI Personas** hardened for production-grade engineering, architectural review, and

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

mandadapumandadapu

Keywords

aiskillspromptsllmclaudeagentsclaude-code

Readme

Agentic-Vault

The Standard for Production-Grade AI Architecture.

Agentic-Vault is a curated library of high-performance AI skills, system prompts, and architectural frameworks. Designed for AI Architects and MLOps Engineers, these tools move beyond basic chat, enabling LLMs to perform complex system design, autonomous agent orchestration, and secure tool integration.

Distribution

Access the skills via GitHub or through our npm package:

npx agentic-vault list --claude

Quick Install

# Install all skills to your preferred platform
npx agentic-vault install --claude    # Claude Code
npx agentic-vault install --cursor    # Cursor
npx agentic-vault install --gemini    # Gemini CLI
npx agentic-vault install --codex     # Codex CLI

Manage Skills Locally

npx agentic-vault list --claude                    # View status
npx agentic-vault disable architect-review --claude # Disable a skill
npx agentic-vault enable architect-review --claude  # Re-enable

The Vault

1. Strategy & Vision

| Skill | Phase | Best For | | :--- | :--- | :--- | | product-vision-architect | Vision | Requirements orchestration, UI/data analysis, roadmapping | | architect-planner | Plan | Requirements discovery, trade-off evaluation, feasibility | | architecture-decision-records | Record | ADR drafting, decision lifecycle, trade-off capture | | documentation-architect | Memorialize | Codebase manuals, C4 model, ebook authoring | | legal-researcher | Legal | Deep research, document cross-referencing |

2. AI Logic & Search

| Skill | Phase | Best For | | :--- | :--- | :--- | | ai-agents-architect | Logic | Multi-agent orchestration, tool design, guardrails | | langchain-architect | Orchestrate | LangChain/LangGraph, LCEL, agentic workflows, memory | | rag-systems-architect | Retrieval | Semantic retrieval, RAG pipelines, GraphRAG, evaluation | | rag-implementation-engineer | RAG Code | Vector DB integration, ingestion pipelines, retrieval logic | | prompt-strategist | Prompts | Prompt engineering, CoT, few-shot, system instructions | | embedding-strategist | Search | Vector search, chunking strategies, re-ranking |

3. Engineering & UI

| Skill | Phase | Best For | | :--- | :--- | :--- | | ui-craftsman | UI Craft | Intentional aesthetics, component craft, premium UI design | | ui-builder | UI Build | React, Next.js, state management, performance, a11y | | mcp-builder | Connect | MCP servers, secure data access, transport design |

4. Infrastructure & Pipeline

| Skill | Phase | Best For | | :--- | :--- | :--- | | k8s-platform-architect | Platform | Enterprise K8s, GitOps, service mesh, multi-tenancy | | container-architect | Artifact | Docker optimization, multi-stage builds, image hardening | | deployment-engineer | Pipeline | CI/CD pipelines, GitOps, progressive delivery, DevSecOps | | mlops-pipeline-architect | ML Pipelines | Vertex AI/Kubeflow, model registry, feature stores, CT | | config-validator | Validate | Schema enforcement, secret validation, drift detection | | mlops-engineer | ML Ops | RAG pipelines, LLM scaling, CI/CD for AI |

5. Safety, Security & Ops

| Skill | Phase | Best For | | :--- | :--- | :--- | | toxic-skills-scanner | Threat Scan | ToxicSkills taxonomy, prompt injection, malicious code detection | | agent-security-hardener | Security | Skill auditing, injection prevention, threat modeling | | skill-audit | Audit | Static security analysis, ToxicSkills detection, read-only audits | | hydra-security-loop | Red Team | Adversarial simulation, closed-loop hardening, automated red-teaming | | compliance-officer | Compliance | GDPR, HIPAA, SOC2, PCI-DSS, audit trails | | deployment-procedures | Safeguard | Go/No-Go criteria, rollback strategy, blast radius control | | incident-response-specialist | Command | Incident command, blameless post-mortems, runbooks | | architect-review | Review | PR reviews, ADR drafting, Distributed Systems |

Manual Usage

For Claude (Web/Projects)

  1. Copy the contents of the .md file from the /skills directory.
  2. Paste it into your Project Instructions or Custom Instructions.
  3. Trigger the skill by name (e.g., "Using the architect-review skill, evaluate this schema...").

For Claude Code (CLI)

Run npx agentic-vault install --claude or add the skill to your global or project-level .claude.json configuration.

Why Agentic-Vault?

Most AI prompts focus on "what to write." Agentic-Vault focuses on "how to think."

  • Type 1 vs Type 2 Decisions: Built-in logic to distinguish between irreversible and reversible choices.
  • Traceability: Forces agents to log "Hidden Thoughts" for better observability.
  • Safety First: Includes guardrails for token loops, prompt injection, and hallucination.

Principles of the Vault

Every skill in this repository is built on four core pillars:

  1. Trade-off Analysis: No solution is perfect; every recommendation must weigh pros and cons.
  2. Context-Awareness: Minimal generic advice; maximum alignment with project constraints.
  3. Risk Identification: Proactively flagging "Type 1" (irreversible) decisions.
  4. Actionable Output: Moving beyond theory to concrete "Refactored Views" and implementation steps.

Contributing

Have a hardened skill you use daily? Pull requests are welcome! All skills are validated against a standard structure on PR — run npm run validate locally to check before submitting.

Please ensure your skill includes:

  • Metadata (Name, Version, Focus)
  • Use This Skill When scenarios
  • Instructions & Constraints with risk categorization
  • Response Format for structured output
  • Behavioral Traits

License

MIT

Maintained by mandadapu. Built for the next generation of AI-augmented engineering.