AgentOps / Harness Governance
Ad Platform Policy Gate Designer
Design policy gates, approval thresholds, deny rules, and bounded execution rules for marketing agents that change bids, budgets, targeting, audiences, feeds, or tracking.
adtech, policy, approvals, dv360, google-ads
Install this skill
Install (Codex)
./bin/skills-hub install agentops/[email protected] --runtime codex
Install (Claude)
./bin/skills-hub install agentops/[email protected] --runtime claude
Install (Generic)
./bin/skills-hub install agentops/[email protected] --runtime generic --target ./my-agent/skills
How You Can Use This
Documentation
Execution: instructions
First run: Read SKILL.md and follow the documented workflow.
Current limits
- Instruction package only; it does not provide or authorize an executable runtime capability.
Classification: declared
Operational Summary
Use when: Use when defining what an ad-platform agent may auto-execute, what requires approval, and what must be denied.
Execution mode: analysis-only
Approval boundary: Analysis-only; must not change live policy, approve campaign changes, or execute platform writes.
Status
Readiness: Experimental
Security reviewed: no
Lifecycle: Active
Runtime & Dependencies
ID: agentops/ad-platform-policy-gate-designer
Runtimes: codex, claude, generic
Tool dependencies: 0
API dependencies: 0
Dependencies
Tools: Not documented
APIs: Not documented
Outputs
- Policy gate table
- Approval threshold map
- Deny rule set
- Audit evidence checklist