6
Published Tools
2
Total Stars
0
Weekly Downloads
5
GitHub Followers
15
Public Repos
100/100
Avg Security
Published Tools
1 Skill5 Agentsacross 3 categoriesDmitry Krivonosov
Data-only defensive playbooks and canonical offline advisory policy pack.
Dmitry Krivonosov
Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests.
...morekrivonosoff161
File-based handoff protocol for AI coding agents + a PreToolUse safety guard.
krivonosoff161
Deterministic pre-filter + cheap→chief escalation pipeline — send only the few items that matter to your expensive model.
...morekrivonosoff161
Cost-aware multi-provider LLM router with role tiers (cheap/mid/chief/audit).
Exact-action operator approval with durable execution coordination and optional effect adapters