Skill Claude CodeCodex
Use this skill when the user wants to enforce a WARD.md security policy inside Google Antigravity via its hook system. Triggers on requests to "secure my Antigravity agent", "block agy from doing X", "install WARD hooks in Antigravity", "make Antigravity respect my policy file", or any work involving the…
Skill Claude CodeCodex
Use this skill when the user wants to enforce a WARD.md security policy inside Claude Code via its native hook system. Triggers on requests to "secure my Claude Code session", "block Claude Code from doing X", "install WARD hooks in Claude Code", "make Claude Code respect my policy file", or any work involving the…
Skill Claude CodeCodex
Use this skill when the user wants to enforce a WARD.md security policy inside Microsoft Agent Framework (MSAF) via its middleware pipeline. Triggers on requests to "secure my Agent Framework agent", "block MSAF from doing X", "add WARD middleware to my agent", "lock down my Copilot SDK agent", or any work involving…
Skill Claude CodeCodex
You have access to @weaveprotocol/adversary v0.2 — a package that generates 68 documented and novel attacks against AI agents and produces standardized scorecards.
Skill Claude CodeCodex
You have access to @weaveprotocol/agentsecbench — a benchmark package that runs locked, versioned attack suites against AI agents and produces tier-graded reports.
Skill Claude CodeCodex
Access Weave Protocol functionality via REST API. Use when MCP tools are unavailable and HTTP access is needed, or when integrating Weave into web applications.
Skill Claude CodeCodex
Use this skill when the user is building, securing, or auditing a browser-based AI agent (Playwright, Puppeteer, Stagehand, browser-use, or custom browser automation). Triggers on requests to "secure my browser agent", "detect prompt injection in web pages", "block my agent from visiting bad URLs", "scan this page for…
Skill Claude CodeCodex
Use this skill when the user wants to set up, audit, or run Weave Protocol security in an AI agent project. Triggers on requests to "set up Weave Protocol", "initialize security", "scaffold security middleware", "audit my dependencies for supply chain risk", "run the Weave dashboard", or "check my Weave…
Skill Claude CodeCodex
Create compliance checkpoints, generate audit reports, and anchor to blockchain. Use when: audit, checkpoint, SOC2, HIPAA, PCI-DSS, ISO27001, GDPR, CCPA, CPRA, blockchain anchor, compliance report, consent management, DSAR, consumer request, opt-out, data breach, retention policy, automated decision.
Skill Claude CodeCodex
Encrypt and decrypt sensitive data using AES-256-GCM or Yoxallismus cipher. Manage secrets in a secure vault. Use when protecting credentials, storing secrets securely, or when the user mentions encrypt, decrypt, vault, or Yoxallismus.
Skill Claude CodeCodex
Use this skill when the user wants to inspect, intercept, or gate AI agent tool calls in real time. Triggers include monitoring agent activity, detecting drift between declared intent and actual actions, checking MCP server reputation, manually approving or blocking suspicious calls, viewing a live feed of agent…
Skill Claude CodeCodex
Integrating Weave Protocol security into LangChain.js applications. Use when building secure LangChain chains, agents, or RAG pipelines with threat detection, prompt injection protection, or PII redaction.
Skill Claude CodeCodex
Scan content for secrets, PII, prompt injection, and dangerous patterns. Vet MCP servers before installation. Use when checking for API keys, detecting personal information, preventing injection attacks, or evaluating MCP server security.
Skill Claude CodeCodex
Use this skill BEFORE executing any install command - npm install, pip install, cargo add, docker pull, or installing IDE extensions (VS Code, Cursor, Windsurf, JetBrains). Triggers on requests to install, add, pull, or use a package, image, or extension - especially when the name was suggested by an AI or pulled from…
Skill Claude CodeCodex
Use this skill when the user wants to define, parse, validate, or enforce security policies for AI agents using the WARD.md standard. Triggers on requests to "add WARD.md", "create agent security policy", "what can this agent do", "lock down this agent", "set up guardrails", "define agent boundaries", or any work…
Skill Claude CodeCodex
Coordinate multi-agent consensus, enforce policies, and manage governance. Use when requiring approval from multiple agents, voting on actions, enforcing policies, or escalating decisions to human review.
Skill Claude CodeCodex
You have access to @weaveprotocol/yoxallismus — an EXPERIMENTAL post-quantum cryptographic composition layer. NOT AUDITED. Use with care.
MCP server Claude CodeCodexCursor +2
AI security scanner - secrets, PII, prompt injection, and exfiltration detection. Runs locally from the @weave_protocol/mund npm package. Needs 2 environment variables to run.