# Agent Ops Governance

> - Operate and govern a fleet of AI agents like managed labor, not shelfware. Use when agent ownership is unclear, AI or token costs are climbing, prototypes have become sprawl, a vendor renewal is approaching, maintenance needs a cadence, or agent tools need pruning. Covers the seven-surface maintenance loop (job, diet, memory, tools, reach, proof, value), tool pruning, three-lane cost measurement, budget signals, fair licensing, a four-state prototype ladder, and one accountable owner per consequential agent. Triggers include agent ownership, cost per completed work unit, prototype graveyards, agent meters versus seats, and keep/change/pause/retire decisions. For security controls, use platform-security-playbook; for ROI math, use platform-roi-scorecard.

## Facts
- Page: https://tashan.sh/capability/skill-cloud-byte-consulting-agent-ops-governance
- tashan id: skill:Cloud-Byte-Consulting/agent-ops-governance
- Source: https://github.com/Cloud-Byte-Consulting/plugins
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 95.0
- Freshness: 90.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: Apache-2.0
- Official: no

## Install

```sh
cp -r agent-ops-governance ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-22 by tashan (https://tashan.sh) from public evidence. Scorer s5.