InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. agentic-os

    Prompts

    Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

    Indexed GitHub, KbWen 236 ★MITUpdated 3 days ago

    git clone https://github.com/KbWen/agentic-os.git
  2. a design skill for claude code, cursor and codex: art direction, reference analysis and browser QA for your frontend

    Stale GitHub, wrg32786 5 ★MITUpdated 12 days ago

    git clone https://github.com/wrg32786/aigent-design-system.git
  3. Universal SEO & GEO skill for AI coding agents: Claude Code, Cursor, Windsurf, GitHub Copilot, Replit, Lovable, Bolt. Optimizes sites for Google, Bing, AI Overviews, ChatGPT and Perplexity.

    Stale GitHub, Aryanpanwar10005 13 ★MITUpdated 30 days ago

    git clone https://github.com/Aryanpanwar10005/seo-geo-optimizer.git
  4. CommandVault

    MCP servers

    Search prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, Agent Skills and MCP servers.

    Stale Official MCP Registry, io.github.geronco Updated 20 days ago 1 note

  5. agent-skills

    Skills

    Agent Skills — agent-neutral autonomous product-building OS for 32+ AI coding tools. 23 skill categories · 28 agents · 149 reference docs · 37 platform variants. One-line prompts → deployed products on Cloudflare Workers.

    Indexed GitHub, heymegabyte 27 ★Custom licence (see repository)Updated today

    git clone https://github.com/heymegabyte/agent-skills.git
  6. Agent Config Bridge

    MCP servers

    Convert CLAUDE.md, AGENTS.md, Cursor rules, GEMINI.md and MCP configs between coding agents.

    Stale Official MCP Registry, io.github.onehumanbeing Updated 33 days ago 1 note

    https://github.com/onehumanbeing/agent-config-bridge/releases/download/v0.1.0/agent-config-bridge-0.1.0.mcpb
  7. product-mode

    Prompts

    The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.

    Indexed GitHub, sohaibt 171 ★MITUpdated 2 days ago

    git clone https://github.com/sohaibt/product-mode.git
  8. Vet third-party AI agent extensions + agent-config files (AGENTS.md, .cursor/rules, CLAUDE.md).

    Stale Official MCP Registry, io.github.temurkhan13 Updated 6 months ago 1 note

    openclaw-skill-vetter-mcp@1.1.2
  9. specpack

    MCP servers

    Audit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects.

    Stale Official MCP Registry, io.github.THE-KIPDEV Updated 59 days ago 3 notes

    specpack@0.1.0
  10. testcase

    Skills

    Agent skills that take a requirement to shipped code: audit the spec, turn it into real tests, then build until every check passes. For Claude Code, ZCode, Cursor and Antigravity.

    Indexed GitHub, xtieume 5 ★MITUpdated 4 days ago

    git clone https://github.com/xtieume/testcase.git
  11. promptstack

    Prompts

    A searchable collection of AI prompts and code gen cursor rules, for bolt.new, loveable, windsurf, trae, to enhance your workflow for developers.

    Stale Archived GitHub, waynesutton 78 ★MITUpdated 25 days ago 1 note

    git clone https://github.com/waynesutton/promptstack.git
  12. agentsync

    Skills

    Sync Claude Code and Cursor rules, skills, and MCP configs from one source of truth. One CLI for Codex, Gemini CLI, and other AI coding agents.

    Indexed GitHub, x0c 9 ★MITUpdated today

    git clone https://github.com/x0c/agentsync.git
  13. agentshield

    MCP servers

    🛡️ Offline Rust security scanner for AI agent tools & MCP servers — MCP, Hermes Agent, CrewAI, LangChain/LangGraph, GPT Actions, Cursor Rules. Catches command injection, credential exfiltration, SSRF & unsafe file access; a typical MCP server scans in <50 ms. CLI, GitHub Action, VS Code, SARIF.

    Indexed GitHub, aiconnai 21 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/aiconnai/agentshield.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.