Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
debate
Datasets & benchmarksAdversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate performance.
git clone https://github.com/lechmazur/debate.git -
claude-sdlc-skills
SkillsAI-native SDLC skills for Claude Code: requirement intake & audit, adversarial review gate, AI test orchestration, decision re-check, release config audit
git clone https://github.com/TsCarpe/claude-sdlc-skills.git -
responsible-prompting-api
PromptsResponsible Prompting is an LLM-agnostic tool that aims at dynamically supporting users in crafting prompts that embed responsible intentions and help avoid harmful, adversarial prompts.
git clone https://github.com/IBM/responsible-prompting-api.git -
ai-berkshire
AI repositoriesAI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.
git clone https://github.com/xbtlin/ai-berkshire.git -
22 production-quality Claude Code Skills for cybersecurity professionals , covering offensive security, defensive operations, reverse engineering, threat hunting, threat intelligence, purple team / adversary emulation, CSOC automation, AI/LLM security, mobile, OT/ICS, GRC, software supply chain security, and more.
git clone https://github.com/Masriyan/Claude-Code-CyberSecurity-Skill.git -
DialectOS
MCP serversSpanish dialect localization MCP server: 25 regional variants, glossary, adversarial QA gates.
-
AgentTrust
MCP serversQuality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
mcp-agenttrust@0.1.1 -
Eclipse Redteam MCP
MCP serversAdversarial simulation for AI agents — sandboxed twins only.
-
ClaudeCode-Workflow-Lab
Agents & frameworksComplete Guide 2026: Claude Code Manual – Workflow Pipelines & Adversarial Budget Loops
git clone https://github.com/Frisher1/ClaudeCode-Workflow-Lab.git -
Fable Mode
MCP serversMechanical write gates, evidence receipts, and adversarial review for AI coding agents.
fable-engine@1.3.5 -
AgentTrust
MCP serversQuality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
mcp-agenttrust@0.1.2 -
agent-conductor
MCP serversAGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.
@cubiczan/agent-conductor@0.1.0 -
TAR Engine
MCP serversAudit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.
tar-engine@0.4.0 -
GAUNTLEX
MCP serversConcurrent Builder + Breaker agents generate code and adversarial tests at once, gated in CI.
gauntlex-ai@1.0.2 -
Edgehound
MCP serversWrites adversarial test suites for AI-built code. Your agent's test engineer.
-
mitre-attack-mcp
MCP serversSearch the MITRE ATT&CK enterprise knowledge base for adversary techniques and tactics.
@mrfentmen/mitre-attack-mcp@1.0.0 -
mitre-atlas-mcp
MCP serversMITRE ATLAS — Adversarial Threat Landscape for AI Systems. Tactics + techniques for attacking AI...
mitre-atlas-mcp@1.0.9 -
irrational
MCP serversAdversarial behavioural-bias engine: audits your decisions for cognitive biases via your own AI.
irrational@0.1.0 -
quorum-alpha-dash
Agents & frameworksAdvanced Multi-Agent AI Crude Oil Trading System with Adversarial Validation 2026
git clone https://github.com/zargarkhan1/quorum-alpha-dash.git -
Second Opinion
MCP serversAdversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.
-
vibe-gate-mcp
MCP serversAdversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock
vibe-gate-mcp@0.1.12 -
agent-collab-skills
SkillsClaude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.
git clone https://github.com/WenyuChiou/agent-collab-skills.git -
SentEdge Idea Machine
MCP serversBuy adversarially-debated AI product ideas over x402: $0.10 pulls, $1 buyouts, USDC on Base.
-
alex-llm-attack-mcp-server
MCP serversQuery and retrieve information about various adversarial tactics and techniques used in cyber atta…
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.