InnerVault

Library

87,246 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. Your AI agent is quietly sabotaging your codebase. Stop the slop with 217 battle-tested anti-patterns, Google SRE enforcement, and a zero-trust diff guard, An Engineering Discipline Playbook & Guard System for AI Coding Agents. Prevent, detect, and audit AI slop and regression.

    Indexed GitHub, imMamdouhaboammar 5 ★MITUpdated today

    git clone https://github.com/imMamdouhaboammar/anti-slop-engineering.git
  2. agent-leash

    Skills

    LEASH-8: an 8-domain control model for AI agents with delegated authority. Scorecard, approval-design checklist, plan-vs-authorize pattern. Patterns from a live production agent operation, sanitized. Free, MIT.

    Stale GitHub, tonydzi 5 ★MITUpdated 4 days ago

    git clone https://github.com/tonydzi/agent-leash.git
  3. Agnostic-AI

    Skills

    Your AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP servers once; apply them identically to Codex, Gemini CLI, Cursor and 16 more. Zero-dependency Node.

    Stale GitHub, ucsandman 24 ★MITUpdated 9 days ago

    git clone https://github.com/ucsandman/Agnostic-AI.git
  4. One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

    Indexed GitHub, yzhao062 262 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/yzhao062/anywhere-agents.git
  5. novibe

    Skills

    Spec-driven development for coding agents — you manage the intent, the machine writes the code. Skills, conventions and git-hook guard rails.

    Stale GitHub, novibe-org 20 ★Apache-2.0Updated 25 days ago

    git clone https://github.com/novibe-org/novibe.git
  6. flagrm

    Skills

    Remove feature flags with your AI coding agent, safely. Skills and guardrails for Claude Code, Copilot and Codex.

    Stale GitHub, dino-cosic 6 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/dino-cosic/flagrm.git
  7. skills

    Skills

    EU compliance enforcement for AI agents. Org-profile-driven guardrails for NIS2, GDPR & ISO 27001 — blocks secrets, flags critical asset impact, enforces data residency, verifies suppliers, tracks incidents with automated deadlines.

    Stale GitHub, eyesecurity 13 ★GPL-3.0Updated 33 days ago

    git clone https://github.com/eyesecurity/skills.git
  8. 🧠 Powerful, tested skills for Claude. Featuring CertMaster OS: turn PDFs, syllabi and lecture transcripts into Obsidian/Notion study notes with quizzes and anti-hallucination guardrails.

    Stale GitHub, HackBepa 16 ★MITUpdated 20 days ago

    git clone https://github.com/HackBepa/claude-skills-hub.git
  9. A coding agent skill pack for non-engineers and vibe coders -- Define/Plan/Build/Verify discipline, plain language, stakes-aware guardrails.

    Stale GitHub, bmtrnavsky 17 ★Custom licence (see repository)Updated 6 days ago

    git clone https://github.com/bmtrnavsky/disciplined-vibe-coding.git
  10. A modular OpenCode engineering framework with persistent Obsidian memory, specialized coding skills, runtime guardrails, evidence-based verification, and Git workflows.

    Stale GitHub, frnkgns 7 ★Updated 25 days ago

    git clone https://github.com/frnkgns/Overgeared-Skills.git
  11. A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

    Indexed GitHub, Sanexxxx777 16 ★MITUpdated 2 days ago

    git clone https://github.com/Sanexxxx777/curated-claude-code.git
  12. devops-ai-kit

    Skills

    Rules, skills, subagents and guardrails that make Claude Code safer for DevOps and cloud infrastructure work (Kubernetes, Terraform, Ansible, Helm, Argo CD, Azure/AWS/GCP).

    Stale GitHub, hoangminhung 6 ★MITUpdated 14 days ago

    git clone https://github.com/hoangminhung/devops-ai-kit.git
  13. aizee

    Skills

    The policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee

    Indexed GitHub, m3taz-ahmed 6 ★MITUpdated 2 days ago

    git clone https://github.com/m3taz-ahmed/aizee.git
  14. Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.

    Indexed GitHub, aks129 34 ★MITUpdated 2 days ago

    git clone https://github.com/aks129/HealthClawGuardrails.git
  15. A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.

    Stale GitHub, steph-dove 16 ★Custom licence (see repository)Updated 23 days ago

    git clone https://github.com/steph-dove/klaussy-agents.git
  16. skraft-plugin

    Skills

    Specialized agents, adversarial reviewers, discipline skills (Outside-In TDD, Clean Architecture) and mechanical guardrails (hooks) for Claude Code and GitHub Copilot.

    Stale GitHub, SebastienDegodez 14 ★GPL-3.0Updated 5 days ago

    git clone https://github.com/SebastienDegodez/skraft-plugin.git
  17. SlashForge

    Skills

    Workflow slash commands for AI coding agents. Spec-driven. Guardrails, not autocomplete.

    Stale GitHub, rajdeepratan 5 ★MITUpdated 4 days ago

    git clone https://github.com/rajdeepratan/SlashForge.git
  18. Agent skill to clean up AI-generated code: audit, refactor and guard vibe-coded codebases with Claude Code, Cursor or Codex. A human approves every decision.

    Stale GitHub, fictormarcel2 5 ★MITUpdated 7 days ago

    git clone https://github.com/fictormarcel2/untangle-everything.git
  19. GenClass

    Skills

    GenClass Runtime: a 10 MB in-browser model that detects race conditions, stale responses and duplicate requests in web apps; opt-in guard mode can prevent some of them. npm i @genclass/runtime

    Indexed GitHub, genclass-dev 11 ★Apache-2.0Updated today

    git clone https://github.com/genclass-dev/GenClass.git
  20. adr-kit

    Skills

    Architecture decisions your AI coding agents actually follow. Ranked ADR retrieval and context injection, deterministic pre-commit and CI enforcement with file:line citations, guided authoring, a staleness guardian, and a key-free MCP server. Native for Claude Code, OpenAI Codex, GitHub Copilot CLI and OpenCode. MIT.

    Stale GitHub, rvdbreemen 13 ★MITUpdated 28 days ago

    git clone https://github.com/rvdbreemen/adr-kit.git
  21. givememod

    Skills

    Claude Code mods on demand — a skill that reads your conversation and builds the mod that fits: plan progress bar, files pane, context gauge, risky-command guard, test watcher. 11 tested templates, 29 building blocks, a map of 3,057 public mods. Terminal and desktop.

    Stale GitHub, timoncool 10 ★MITUpdated 21 days ago

    git clone https://github.com/timoncool/givememod.git
  22. The working rules (skills) the cross-model Neo.mjs agent team loads every session: ticket intake, PR review gates, lane coordination and guards, versioned as one package. For apps built on Neo.mjs, for contributors, and for anyone who wants to read them.

    Indexed GitHub, neomjs 11 ★MITUpdated 3 days ago

    git clone https://github.com/neomjs/neo-agent-skills.git
  23. agent-skills

    Skills

    🧰 55 Agent Skills: resolve merge conflicts, guardrail your agent, TDD, fix architecture, polish UI, roast your GitHub, bisect bugs and catch AI slop. Tested, one-line install. Claude Code, Cline, Cursor, Codex

    Stale GitHub, milad-ahmd 5 ★MITUpdated 14 days ago

    git clone https://github.com/milad-ahmd/agent-skills.git
  24. planwright

    Skills

    Autopilot for spec-driven development on Claude Code: sign off a spec and a guardrailed agent fleet builds, reviews, and delivers draft PRs. Scales from one feature to an agentic software factory. You keep sign-off and merge.

    Stale GitHub, inkatze 5 ★MITUpdated 13 days ago

    git clone https://github.com/inkatze/planwright.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.