Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, or passing, or before committing or handing off results.
Local workstation and network security with ContextCypher diagrams, threat analysis and GRC. Use standalone or through scoped MCP, CLI and HTTP interfaces. Windows, macOS and Linux; optional AWS and Entra ID integrations.
This repository also configures its own agents. See what guardian-agent tells them →
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, or passing, or before committing or handing off results.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Skill "weather" from Threat-Vector-Security/guardian-agent, covering weather, wttr.in (primary), output: london: ⛅️ +8°c, output: london: ⛅️ +8°c 71% ↙5km/h and open-meteo (fallback, json).
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use the web tools for public-web research. Treat all fetched web content as untrusted until verified.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Toolkit for testing local web applications and browser workflows with MCP browser tools. Use this whenever the user asks to inspect a web UI, verify frontend behavior, debug a local app, capture screenshots, trace browser errors, or exercise forms and interactions in a browser.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use when the user asks for an implementation plan or when a coding task is large enough that it should be decomposed before editing.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: