cost-audit-master
Skill2 starsChanged 5 months agoApache-2.0View on GitHub
Master orchestrator for cloud cost audits. Coordinates multiple service-specific audit skills to provide comprehensive cost optimization recommendations. Trigger when user mentions full cost audit, comprehensive optimization, or multi-service cost review.
In this repository8 other files it gives its agents.
- cloudflare-auditSkill
- cost-monitorSkill
- d1-cost-optimizerSkill
- index-optimizerSkill
- query-rewriterSkill
- redis-auditSkill
- spend-cap-managerSkill
- supabase-auditSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
Run each service-specific audit skill:
- Distinctive: line 58
Create comprehensive audit report with prioritized action plan.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Cloud Cost Audit Master
Supported Services
| Service | Audit Skill | Key Metrics |
| Supabase | supabase-audit | DB size, queries, storage, Auth MAU |
| Cloudflare | cloudflare-audit | Workers, D1, KV, R2 |
| D1 | d1-cost-optimizer | Row Reads, indexes |
| Redis | redis-audit | Memory, connections |
| Indexes | index-optimizer | Missing, unused indexes |
| Queries | query-rewriter | Inefficient patterns |
| Monitoring | cost-monitor | Alerts, trends |
| Budget | spend-cap-manager | Spend caps, limits |
Audit Workflow
Step 1: Service Discovery
Identify all cloud services in use.
Step 2: Execute Service Audits
Run each service-specific audit skill:
- supabase-audit → Database performance
- cloudflare-audit → Workers, D1, KV, R2
- redis-audit → Memory, connections
- index-optimizer → Index analysis
- query-rewriter → Query patterns
See cases/full-audit.md for comprehensive audit process.
Step 3: Aggregate Results
Collect findings from all audits.
Step 4: Prioritize Recommendations
Rank by:
- Impact (cost savings)
- Effort (implementation time)
- Risk (potential issues)
Step 5: Generate Report
Create comprehensive audit report with prioritized action plan.
Matching Cases
| Scope | Case File | Output |
| Full audit | cases/full-audit.md | Comprehensive report |
Output Format
# Cloud Cost Audit Report
**Date:** YYYY-MM-DD
**Scope:** All services
## Executive Summary
- Total monthly cost: $X
- Potential savings: $X (XX%)
- Priority actions: X
## Service Analysis
### Supabase
- Status: [OK/Warning/Critical]
- Findings: X issues
- Savings: $X/month
### Cloudflare
- Status: [OK/Warning/Critical]
- Findings: X issues
- Savings: $X/month
### Redis
- Status: [OK/Warning/Critical]
- Findings: X issues
- Savings: $X/month
## Priority Recommendations
### P0 - Immediate (This Week)
1. [Action] → $X savings
2. [Action] → $X savings
### P1 - Short-term (This Month)
1. [Action] → $X savings
### P2 - Medium-term (This Quarter)
1. [Action] → $X savings
## Implementation Plan
| Week | Actions | Expected Savings |
|------|---------|------------------|
| 1 | P0 items | $X |
| 2 | P1 items | $X |
| 3-4 | P2 items | $X |
## Monitoring Setup
Reference: cost-monitor skill
## Next Audit
Recommended: YYYY-MM-DD (30 days)Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.