Collected sources and patterns will appear here. Add from search or the patterns library.
ToolCallProposal -> PolicyDecision
Evaluate proposed tool call arguments against safety and compliance DSL rules to block hazardous commands prior to execution.
Problem it solves
Agents generate destructive or insecure arguments (e.g., SQL injections, path traversals) dynamically.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.