| name | non-destructive-infinity-guard |
| description | Always-on action boundary, risk classifier, and mutation approval gate for Yuri OS. Use when a user or agent invokes /yuri guard, /guard, or /ndig, or when any proposed action, tool call, or mutation needs risk classification, scope verification, and approval before execution. |
| version | 1.0.0 |
| status | active |
| enterprise_ready | true |
| non_destructive_default | true |
| triggers | ["/yuri guard","/guard","/ndig"] |
| requires | ["enterprise-control-plane","audit-events","rollback-policy"] |
| scope | harness |
| invocation | ability |
Non-Destructive Infinity Guard Skill
When to use
Use this skill when the user asks Yuri OS / Yuri to perform work involving:
- proposed_action
- target_path
- tool_call
- domain_manifest
- risk_context
- user_permission_state
Also use it when the active task matches this operating principle:
Maintain a continuous protective boundary between user intent, agent plans, tool calls, file operations, and core system state. Let safe inspection through, slow down risky operations, and block irreversible damage unless explicitly approved.
When not to use
Do not use this skill when:
- the task is trivial and does not need system-level treatment
- no target, goal, or evidence source is available
- the user explicitly requests no architectural expansion
- the task would require destructive action without approval
- the extension would duplicate an already active domain without adding value
Trigger phrases
- "run non-destructive-infinity-guard"
- "use Non-Destructive Infinity Guard"
- "turn this into Yuri OS DNA"
- "analyze and integrate this safely"
- "enterprise-ready extension"
- "non-destructive implementation plan"
- "bake this into the system"
Required inputs
input:
goal: string
artifact_type: proposed_action | target_path | tool_call | domain_manifest | risk_context | user_permission_state
target: string
constraints:
enterprise_mode: true
destructive_actions_allowed: false
require_audit_trail: true
[]
