Skill Claude CodeCodex
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
Sync one reviewed context source into native AI-agent files, with privacy-safe evidence receipts that never confuse generation with runtime load.
Skill Claude CodeCodex
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
Skill Claude CodeCodex
Use when a task must obey a hard project policy, such as "do not generate tests for internal services", "do not call production APIs", or "do not edit generated files". Emits a privacy-safe receipt before writes and after guard checks.
Skill Claude CodeCodex
Emit privacy-safe evidence attestations for agent actions, reviews, memory answers, handoffs, scores, approvals, and tool dispatches.