InnerVault

Library

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

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. skill-doctor

    Skills

    🩺 A bilingual meta-skill for Claude Code: health-check your other skills and review agent-workflow architecture - runtime reality, ownership, scaffolding, recovery. Diagnose-only. Built on Matt Pocock's method.

    Stale GitHub, isalicema 7 ★MITUpdated 11 days ago

    git clone https://github.com/isalicema/skill-doctor.git
  2. 82 ready-to-deploy agents for Microsoft Copilot Chat, no Copilot Premium required. Paste the instruction block into the Copilot Studio builder. Writing, HR, PM, IT ops, Sales, Finance, Engineering and more. RAI reviewed, source-quality labelled, tested. No coding.

    Stale GitHub, kesslernity 117 ★CC-BY-SA-4.0Updated 13 days ago

    git clone https://github.com/kesslernity/awesome-copilot-chat-agents.git
  3. hunch

    MCP servers

    Shared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.

    Stale Official MCP Registry, io.github.davesheffer Updated 2 months ago 1 note

    @davesheffer/hunch@1.38.1
  4. The battle-tested Claude Code kit behind HasBrainsAI — agent skills, subagents & slash commands for production multi-agent systems. Install in one command.

    Stale GitHub, endorphin-ai 9 ★MITUpdated 34 days ago

    git clone https://github.com/endorphin-ai/hasbrains-agent-kit.git
  5. tempest

    Tools & apps

    Agentic Engineering that actually scales. Run Claude Code, Codex, Gemini and any other CLI Agents in parallel with upto 86% fewer tokens and 92% fewer tool calls

    Stale GitHub, tempestai-dev 196 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/tempestai-dev/tempest.git
  6. codex-factory

    Agents & frameworks

    Multi-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact verification for Codex.

    Stale GitHub, yueheng-rgb 99 ★MITUpdated 2 months ago

    git clone https://github.com/yueheng-rgb/codex-factory.git
  7. jakehandy.com

    MCP servers

    Search, read, cite and react to Jake Handy's writing on AI, music tech and agentic engineering.

    Stale Official MCP Registry, com.jakehandy Updated 2 months ago 1 note

  8. claude-skills

    Skills

    410 Claude Code skills & agent skills & plugins (120+ Agents, custom commands, 410+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

    Indexed GitHub, alirezarezvani 29.9k ★MITUpdated today

    git clone https://github.com/alirezarezvani/claude-skills.git
  9. WorldLines

    Agents & frameworks

    Agents for Role Play. Agents for Game. Agents as a Game. An orchestrator-agents engine for living worlds — file-backed, event-sourced.

    Stale GitHub, LudicDynamics 107 ★Custom licence (see repository)Updated 21 days ago

    git clone https://github.com/LudicDynamics/WorldLines.git
  10. agent-alchemy

    Skills

    Agent Alchemy is a curated collection of plugins, apps, and extensions designed to elevate your agentic engineering workflows. Built for Claude Code and other AI coding agents, these tools help developers work smarter and ship faster.

    Stale GitHub, sequenzia 45 ★MITUpdated 5 months ago

    git clone https://github.com/sequenzia/agent-alchemy.git
  11. dev-flow

    Skills

    A filesystem contract (.workflow/meta.json) + 55 agent skills that take a product from idea to production: web (Next.js 16), mobile (Expo/RN), an eve agent engine, scrum on Linear/Jira/GitHub, a design-system lint, registry intake, a post-deploy debt audit, EU data residency. Runs on Claude Code, Codex, Copilot, Gemini, Cursor.

    Stale GitHub, lukedj78 6 ★MITUpdated 26 days ago

    git clone https://github.com/lukedj78/dev-flow.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.