>_Skillful
Need help with advanced AI agent engineering?Contact FirmAdapt
Debashish Ghosal

Debashish Ghosal

@deghosal-2026

AI-Native Engineering Leader | Building Agentic DevOps with LangGraph | Developer Productivity & Business Efficiency | ex-Microsoft · ex-Nordstrom · WBD | MBA ·

Seattle, WA On GitHub since May 2026

6

Published Tools

9

Total Stars

27

Weekly Downloads

6

GitHub Followers

17

Public Repos

100/100

Avg Security

Published Tools

2 MCP Servers1 Skill3 Agentsacross 3 categories

Composable tool mesh for MCP ecosystems

MCP Serveruncategorised
23 dirs

Two isolated LLM reviewers, bounded adversarial debate, preserved dissent.

Agentai-agents
21 dir

Multi-model LLM tier router with cost-per-completed-task accounting

Skillai-ml
21 dir

deghosal-2026

Continuous adversarial-testing (proof) engine for AI-agent defenses — run curated attack packs against the deployed stack, verify enforcement with the kill-chain, and publish an honest, reproducible defense benchmark.

...more
Agentai-agents
21 dir

Debashish Ghosal

Stateless HTTP proxy that exposes any REST API as an MCP tool

MCP Serveruncategorised
12 dirs

deghosal-2026

Hierarchical task planning with an independent LLM critic. A planner decomposes a goal into a typed plan; a critic audits every subtask; the plan is revised until approval — or escalated to a human.

...more
Agentai-agents
1 dir