create-policies

# Create Guard Policies Help developers define, import, and test guard policies that control what agents can and cannot do. ## Policy Types | Type | Purpose | Example | |------|---------|---------| | `risk_threshold` | Block/warn when risk score exceeds limit | Block actions with risk > 80 | | `action_type_restriction` | Allow/deny specific action types | Block `security` actions without approval | | `approval_gate` | Require human approval for matching actions | Require approval for deploys | | `webhook_check` | Call external endpoint for policy decision | Check Jira ticket status before deploy | | `semantic_guardrail` | LLM-based content analysis | Block PII in action metadata | ## Guard Modes - **`off`** — No policy enforcement (development only) - **`warn`** — Log policy violations but allow execution - **`enforce`** — Block policy violations (production recommended) ## Defining Policies in YAML ### Risk Threshold Policy ```yaml name: high-risk-blocker type: risk_threshold mode: enforce conditions: risk_score_min: 80 reversible: false action: block reason: "Irreversible actions with risk >= 80 require manual execution" ``` ### Action Type Restriction ```yaml name: no-unattended-deploys type: action_type_restriction mode: enforce conditions: action_types: - deploy - database action: require_approval reason: "Deploy and database actions require human approval" ``` ### Approval Gate ```yaml name: production-approval-gate type: approval_gate mode: enfor...