Skill 1
Trace envelope writer
Use when a no-write agent run needs a structured trace envelope before proposed actions are reviewed for promotion.
Back to Skill Library
Agent governance workflow library
Shadow mode trace review
Review no-write agent traces, policy decisions, human corrections, near misses, rollback readiness, and canary scope before agents get write access.
This is a complete workflow library with 5 individual skills. Download the full library or pick the specific skill folder your team needs first.
Individual skills in this library
Use one skill at a time, or keep the full workflow together.
Some AI tools expect one skill folder per upload. Download the full library when you want the whole workflow, or download an individual skill when you only need one job done.
Skill 2
No-write action simulator
Use when a write-capable action must be replaced with a no-op, dry-run, policy-blocked, or simulated result before live execution.
Skill 3
Policy decision logger
Use when proposed agent actions need allow, deny, modify, or escalate decisions recorded before side effects occur.
Skill 4
Human correction reviewer
Use when proposed shadow actions need comparison against human approvals, rejections, corrections, and rationale.
Skill 5
Canary promotion gatekeeper
Use when a team needs to decide whether shadow traces justify a constrained live canary, continued shadow mode, or blocked write access.
Security fit check
Is the public Shadow mode trace review library enough, or does this need deeper review?
Use the public library when the workflow is low-risk, the inputs are already sanitized, and a team member can review the output before it reaches a buyer or customer.
Do deeper review when this workflow touches real tools, data sources, role ownership, approval paths, or customer-facing output.
Write access reviewAI OperationsSecurityPlatform EngineeringWorkflow OwnerRevOps
Good deeper-review trigger signals
- The workflow touches customer, prospect, CRM, proposal, security, pricing, or campaign data.
- Different teams disagree on the approved source of truth.
- The AI output could become customer-facing, revenue-impacting, or compliance-sensitive.
- You need reusable eval checks before asking more people to use the workflow.