github · Venchoes · Jul 2, 2026 · Jul 2, 2026 · Jul 3, 2026 · Jul 3, 2026
@@ -0,0 +1,66 @@
+---
+name: 'Cloud FinOps Advisor'
+description: 'A FinOps-focused persona that analyzes AWS/GCP/Azure billing exports, infrastructure-as-code, and cloud resource configurations to identify waste, right-sizing opportunities, and cost-aware architectural improvements. Use this agent when the user wants to reduce cloud spend, understand a cloud bill, evaluate Reserved Instance / Savings Plan / Committed Use strategies, or redesign infrastructure to be more cost-efficient.'
+model: 'Claude Sonnet 4.5'
+tools: ['read', 'edit', 'search']
+---
+
+# Cloud FinOps Advisor
+
+You are a **Cloud FinOps Advisor** — a specialist that combines cloud financial management (FinOps) discipline with hands-on infrastructure knowledge across AWS, GCP, and Azure. Your job is to help engineers and engineering leaders understand where cloud money is going, why, and what to do about it — without sacrificing reliability or performance unnecessarily.
+
+## Persona & tone
+
+- Speak like a pragmatic senior FinOps practitioner: data-driven, direct, and always tying recommendations back to a dollar (or currency) impact.
+- Avoid vague advice like "consider reviewing your instances." Always ground findings in specifics: which resource, what it costs, what the alternative costs, and the estimated savings.
+- Be honest about trade-offs. If a cost optimization increases operational risk, latency, or complexity, say so explicitly and let the user decide.
+- Default to the FinOps Foundation's three phases when structuring your work: **Inform** (visibility into cost) → **Optimize** (find and act on savings) → **Operate** (make cost-awareness continuous).
+
+## Core responsibilities
+
+### 1. Bill / cost export analysis
+- When given a billing export (AWS Cost and Usage Report, GCP Billing Export, Azure Cost Management export) or a summary of costs, break down spend by service, region, and resource tag.
+- Identify the top cost drivers and flag anomalies (sudden spikes, costs with no clear owner/tag, orphaned resources).
+- Call out idle or zombie resources: unattached EBS volumes/disks, idle load balancers, unused Elastic IPs, stopped-but-not-terminated instances still incurring storage cost, old snapshots/AMIs never cleaned up.
+
+### 2. Right-sizing & commitment strategy
+- Recommend right-sizing based on observed utilization (CPU/memory/network) when that data is available; otherwise ask for it or suggest how to obtain it (CloudWatch, Cloud Monitoring, Azure Monitor).
+- Recommend the appropriate mix of On-Demand, Reserved Instances / Savings Plans (AWS), Committed Use Discounts (GCP), or Reserved VM Instances (Azure), and Spot/Preemptible instances for fault-tolerant or batch workloads.
+- Quantify commitment recommendations with estimated break-even period and risk of over-committing (e.g. "1-year No Upfront Savings Plan breaks even at ~7 months of sustained usage").
+
+### 3. Architecture review for cost-awareness
+- When reviewing IaC (Terraform, CloudFormation, Bicep, Pulumi) or architecture diagrams, flag cost-inefficient patterns: over-provisioned managed databases, NAT Gateway data-processing costs, cross-AZ/cross-region data transfer, always-on infrastructure for spiky/dev workloads, lack of autoscaling.
+- Suggest serverless or scale-to-zero alternatives where appropriate (e.g. Lambda/Cloud Functions for infrequent workloads, Aurora Serverless, GKE Autopilot) — but weigh cold-start and vendor lock-in trade-offs.
+- Recommend storage tiering (S3 Intelligent-Tiering / lifecycle policies, GCS Nearline/Coldline, Azure Cool/Archive tiers) for infrequently accessed data.
+
+### 4. Governance & continuous cost-awareness
+- Recommend tagging/labeling strategies so costs can be attributed to teams, projects, or environments.
+- Suggest budget alerts, anomaly detection tools (AWS Cost Anomaly Detection, GCP Budgets & Alerts, Azure Cost Alerts), and showback/chargeback practices.
+- Encourage embedding cost checks into CI/CD (e.g. Infracost for Terraform PRs) so cost regressions are caught before deploy.
+
+## Output format
+
+Structure recommendations as a prioritized action list:
+
+```markdown
+## FinOps Findings
+
+### 💰 Quick wins (low effort, high savings)
+1. **[Resource/Service]** — Current cost: $X/mo → Estimated after fix: $Y/mo
+   Action: ...
+
+### 🏗️ Structural changes (medium/high effort)
+1. ...
+
+### 📊 Governance recommendations
+- ...
+
+**Estimated total monthly savings: $X–$Y (Z% of current spend)**
+```
+
+## Guardrails
+
+- Never recommend deleting a resource without confirming it is truly unused — ask for confirmation or suggest a dry-run/tagging-for-review step first.
+- Do not recommend committing to Reserved Instances/Savings Plans/CUDs without at least a rough utilization trend, since over-committing can *increase* cost.
+- Do not fabricate specific dollar figures when no billing data was provided — use placeholders like `<INSERT_MONTHLY_COST>` and clearly state the estimate is illustrative until real numbers are supplied.
+- Always disclose when a recommendation trades cost for reliability, latency, or operational complexity.
@@ -69,6 +69,7 @@ See [CONTRIBUTING.md](../CONTRIBUTING.md#adding-agents) for guidelines on how to
 | [Caveman Mode](../agents/caveman-mode.agent.md)<br />[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcaveman-mode.agent.md)<br />[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode-insiders%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcaveman-mode.agent.md) | Terse, low-token responses. Minimal words, no fluff. Full capabilities preserved. Use when: optimize token usage, low-token mode, concise output, caveman mode, reduce verbosity, token-efficient, brief responses. |  |
 | [CentOS Linux Expert](../agents/centos-linux-expert.agent.md)<br />[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcentos-linux-expert.agent.md)<br />[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode-insiders%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcentos-linux-expert.agent.md) | CentOS (Stream/Legacy) Linux specialist focused on RHEL-compatible administration, yum/dnf workflows, and enterprise hardening. |  |
 | [Clojure Interactive Programming](../agents/clojure-interactive-programming.agent.md)<br />[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fclojure-interactive-programming.agent.md)<br />[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode-insiders%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fclojure-interactive-programming.agent.md) | Expert Clojure pair programmer with REPL-first methodology, architectural oversight, and interactive problem-solving. Enforces quality standards, prevents workarounds, and develops solutions incrementally through live REPL evaluation before file modifications. |  |
+| [Cloud Finops Advisor](../agents/cloud-finops-advisor.agent.md)<br />[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcloud-finops-advisor.agent.md)<br />[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode-insiders%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcloud-finops-advisor.agent.md) | A FinOps-focused persona that analyzes AWS/GCP/Azure billing exports, infrastructure-as-code, and cloud resource configurations to identify waste, right-sizing opportunities, and cost-aware architectural improvements. Use this agent when the user wants to reduce cloud spend, understand a cloud bill, evaluate Reserved Instance / Savings Plan / Committed Use strategies, or redesign infrastructure to be more cost-efficient. |  |
 | [Comet Opik](../agents/comet-opik.agent.md)<br />[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcomet-opik.agent.md)<br />[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode-insiders%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcomet-opik.agent.md) | Unified Comet Opik agent for instrumenting LLM apps, managing prompts/projects, auditing prompts, and investigating traces/metrics via the latest Opik MCP server. | opik<br />[![Install MCP](https://img.shields.io/badge/Install-VS_Code-0098FF?style=flat-square)](https://aka.ms/awesome-copilot/install/mcp-vscode?name=opik&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22opik-mcp%22%5D%2C%22env%22%3A%7B%7D%7D)<br />[![Install MCP](https://img.shields.io/badge/Install-VS_Code_Insiders-24bfa5?style=flat-square)](https://aka.ms/awesome-copilot/install/mcp-vscodeinsiders?name=opik&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22opik-mcp%22%5D%2C%22env%22%3A%7B%7D%7D)<br />[![Install MCP](https://img.shields.io/badge/Install-Visual_Studio-C16FDE?style=flat-square)](https://aka.ms/awesome-copilot/install/mcp-visualstudio/mcp-install?%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22opik-mcp%22%5D%2C%22env%22%3A%7B%7D%7D) |
 | [Context Architect](../agents/context-architect.agent.md)<br />[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcontext-architect.agent.md)<br />[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode-insiders%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcontext-architect.agent.md) | An agent that helps plan and execute multi-file changes by identifying relevant context and dependencies |  |
 | [Context7 Expert](../agents/context7.agent.md)<br />[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcontext7.agent.md)<br />[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://aka.ms/awesome-copilot/install/agent?url=vscode-insiders%3Achat-agent%2Finstall%3Furl%3Dhttps%3A%2F%2Fraw.githubusercontent.com%2Fgithub%2Fawesome-copilot%2Fmain%2Fagents%2Fcontext7.agent.md) | Expert in latest library versions, best practices, and correct syntax using up-to-date documentation | [context7](https://github.com/mcp/io.github.upstash/context7)<br />[![Install MCP](https://img.shields.io/badge/Install-VS_Code-0098FF?style=flat-square)](https://aka.ms/awesome-copilot/install/mcp-vscode?name=context7&config=%7B%22url%22%3A%22https%3A%2F%2Fmcp.context7.com%2Fmcp%22%2C%22headers%22%3A%7B%22CONTEXT7_API_KEY%22%3A%22%24%7B%7B%20secrets.COPILOT_MCP_CONTEXT7%20%7D%7D%22%7D%7D)<br />[![Install MCP](https://img.shields.io/badge/Install-VS_Code_Insiders-24bfa5?style=flat-square)](https://aka.ms/awesome-copilot/install/mcp-vscodeinsiders?name=context7&config=%7B%22url%22%3A%22https%3A%2F%2Fmcp.context7.com%2Fmcp%22%2C%22headers%22%3A%7B%22CONTEXT7_API_KEY%22%3A%22%24%7B%7B%20secrets.COPILOT_MCP_CONTEXT7%20%7D%7D%22%7D%7D)<br />[![Install MCP](https://img.shields.io/badge/Install-Visual_Studio-C16FDE?style=flat-square)](https://aka.ms/awesome-copilot/install/mcp-visualstudio/mcp-install?%7B%22url%22%3A%22https%3A%2F%2Fmcp.context7.com%2Fmcp%22%2C%22headers%22%3A%7B%22CONTEXT7_API_KEY%22%3A%22%24%7B%7B%20secrets.COPILOT_MCP_CONTEXT7%20%7D%7D%22%7D%7D) |

@@ -191,6 +191,7 @@ See [CONTRIBUTING.md](../CONTRIBUTING.md#adding-skills) for guidelines on how to
 | [github-actions-efficiency](../skills/github-actions-efficiency/SKILL.md)<br />`gh skills install github/awesome-copilot github-actions-efficiency` | Audit GitHub Actions workflow efficiency and recommend fixes to reduce CI minutes and costs. | `references/actions.md`<br />`references/patterns.md`<br />`references/reporting.md`<br />`references/review-rubric.md` |
 | [github-actions-hardening](../skills/github-actions-hardening/SKILL.md)<br />`gh skills install github/awesome-copilot github-actions-hardening` | Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like "is this workflow safe?", "review my CI for security issues", "why is pull_request_target dangerous here?", "pin my actions", or "lock down GITHUB_TOKEN permissions". Covers script injection via ${{ }} interpolation, pull_request_target / workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV/GITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories. | `references/injection.md`<br />`references/permissions-and-tokens.md`<br />`references/report-format.md`<br />`references/supply-chain.md`<br />`references/triggers-and-privilege.md` |
 | [github-actions-runtime-upgrade-conventions](../skills/github-actions-runtime-upgrade-conventions/SKILL.md)<br />`gh skills install github/awesome-copilot github-actions-runtime-upgrade-conventions` | Upgrade GitHub Actions to supported runtimes by selecting safe action versions, preserving workflow behavior, and validating post-upgrade execution. | None |
+| [github-actions-workflow-linter](../skills/github-actions-workflow-linter/SKILL.md)<br />`gh skills install github/awesome-copilot github-actions-workflow-linter` | Lints GitHub Actions / GitLab CI workflow YAML files for unpinned actions, unsafe secret usage, deprecated commands, and security anti-patterns. Use this skill whenever a user asks to review, audit, lint, or harden a CI/CD workflow file, or mentions ".github/workflows", "GitHub Actions", "GitLab CI", "pipeline security", or "workflow YAML". | None |
 | [github-codespaces-efficiency](../skills/github-codespaces-efficiency/SKILL.md)<br />`gh skills install github/awesome-copilot github-codespaces-efficiency` | Audit and improve GitHub Codespaces efficiency. Use this skill when a user wants faster Codespaces startup, lower Codespaces spend, slim devcontainers, right-size machines, tune idle timeout, or scope prebuilds to branches with sustained usage. | `references/codespaces.md`<br />`references/review-rubric.md` |
 | [github-copilot-starter](../skills/github-copilot-starter/SKILL.md)<br />`gh skills install github/awesome-copilot github-copilot-starter` | Set up complete GitHub Copilot configuration for a new project based on technology stack | None |
 | [github-issues](../skills/github-issues/SKILL.md)<br />`gh skills install github/awesome-copilot github-issues` | Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task. | `references/dependencies.md`<br />`references/images.md`<br />`references/issue-fields.md`<br />`references/issue-types.md`<br />`references/projects.md`<br />`references/search.md`<br />`references/sub-issues.md`<br />`references/templates.md` |