>_Skillful
Need help with advanced AI agent engineering?Contact FirmAdapt
John-mg

John-mg

@john-mg

On GitHub since May 2020

6

Published Tools

0

Total Stars

66

Weekly Downloads

0

GitHub Followers

2

Public Repos

Published Tools

2 MCP Servers2 Skills2 Agentsacross 3 categories

@merchantguard/guardbot-skills

john-mg

Compliance passports for AI agents - OpenClaw skill for GuardBot verification

SkillAI Tool
1 dir

@agentguard-run/mcp

john-mg

AgentGuard MCP server: local spend caps, kill-switch style blocking, and Ed25519-signed provenance receipts for AI agent actions. Zero data plane: prompts never pass through this server.

...more
MCP Serveruncategorised
66/wk2 dirs

@merchantguard/agentguard-cb

john-mg

Open-source CE 3.0 evidence SDK for Stripe disputes. MIT licensed. No LLM in the evidence pipeline.

MCP ServerLLM Tool
1 dir

@agentguard-run/spend

john-mg

Local-runtime spend caps and capability-gated model routing for AI agents. Prompts, API keys, and signing keys stay inside the customer runtime. Zero data plane involvement.

...more
AgentLLM Tool
1 dir

@merchantguard/sentinela

john-mg

Conversational Intent Firewall for AI agents. Screen WhatsApp, Telegram, and chat messages for prompt injection, social engineering, and fraud in <10ms.

...more
AgentLLM Tool
1 dir

@agentguard-run/burn

john-mg

Local session usage and runaway-agent circuit breaker. Explain tokens, cache rewrites and API list cost, track pace, warn on heavy turns, and gate agent fan-out with signed receipts. Nothing leaves the machine.

...more
SkillLLM Tool
1 dir