Finance & Compliance
Cost Optimizer
Cost Optimizer scans spend patterns and turns them into a prioritized list of savings opportunities. It helps teams understand where money is leaking, what changes would matter most, and how to communicate those recommendations clearly. Engineering leaders, finance operators, and platform teams benefit when cloud and AI costs are growing faster than visibility. The skill is useful for recurring optimization reviews, budget conversations, and identifying quick wins without manually digging through every line item. Its production-grade advantage is prioritization. The output emphasizes ranked recommendations, projected savings, and a concise summary so the review can drive real action rather than producing another dense cost report.
One-Time Purchase
$19.99
Cost Optimization Brief — NovaTech Solutions
Reviewed spend: $127,400 across compute, database, and AI/LLM line items last month.
Headline
Four ranked moves recover $18,200/month ($218,400/year) against current run-rate. Two of them — a model swap on the classification pipeline and idle-EBS cleanup — land within two weeks at low risk. The 1-year EC2 Savings Plan is the biggest single line item but only makes sense after the rightsizing finishes.
Total projected reduction at full execution. $8.6K of that is committable in the first 14 days; the remaining $9.6K depends on the rightsizing landing cleanly so the Savings Plan covers steady-state, not pre-rightsize peaks.
Ranked Opportunities
| # | Opportunity | Category | Monthly Savings | Priority | Risk |
|---|---|---|---|---|---|
| 1 | Switch classification pipeline GPT-4o → GPT-4o-mini | AI/LLM | $4,200 | P0 | Low |
| 2 | Rightsize 3 RDS instances (db.r6g.xlarge → db.r6g.large) | Database | $3,560 | P1 | Medium |
| 3 | Delete 14 unattached EBS volumes | Compute | $840 | P0 | Low |
| 4 | 1-year Savings Plan on stable EC2 fleet | Compute | $9,600 | P1 | Low |
| 5 | Enable prompt caching on support-ticket Claude calls | AI/LLM | $960 | P2 | Low |
Before / After — Classification Pipeline
Current
GPT-4o on every classification call
~2.1M calls/mo, avg 600 input tokens
Proposed
GPT-4o-mini routed to same prompt
Fallback to GPT-4o if confidence < 0.7
The 500-sample re-eval was run against the same labeled fixture the team used at GA. Accuracy drift was 0.3 points — inside measurement noise. The confidence-gated fallback protects the edge cases.
Risk of Action
RDS rightsizing
Maintenance window required. The three instances chosen have p99 CPU under 35% over the trailing 90 days, but two of them spike on the monthly close job. Schedule the resize for the first week of the cycle, not the last.
Savings Plan timing
Buying the Savings Plan before the rightsizing completes locks in commitment to current oversized instances. Sequence: rightsize first, run two weeks at the new shape to confirm steady-state, then commit.
EBS cleanup
All 14 volumes have been detached for 60+ days and have no associated snapshots tagged for retention. Confirm with the platform team that nothing in the disaster-recovery runbook references these volume IDs before deletion.
Recommended Sequence
Four-week rollout
This sample illustrates the skill's output format. Figures are illustrative; ClearPoint Nexus is not affiliated with the companies named.
View full sample →
All sales final. No refunds on digital products.
Includes support for Claude Code, Codex, OpenClaw, and Google Antigravity in the same license.
Also in FinOps & Compliance
Bundle price: $55. Compare this skill with the full workflow bundle or Pro access.
Best for
Engineering leaders and platform teams running a quarterly FinOps review on AWS, GCP, or Azure spend in the $20K–$500K monthly range, and AI engineering leads watching their OpenAI / Anthropic bill creep past a comfort threshold. Most useful when the team can act on prioritized recommendations — reserved instances, idle resources, model-tier downgrades — within the next sprint.
Not ideal for
Startups still at hobby-level cloud spend (under a few hundred dollars per month) where the optimization findings are smaller than the time spent reading them. Also a poor fit for fixed-price hosting (Vercel team plan, Heroku) where there are no real levers to pull.
Included in this purchase
- Claude Code, Codex, OpenClaw, and Google Antigravity skill files.
- Setup guidance for the right adapter in your workspace.
- One-time license for the purchased skill version.
Setup
Plan for a short copy-and-configure setup in your preferred agent workspace. No custom integration is required for the skill file itself.
Related Skills
$19.99
One-time license
$19.99
One-time license
$19.99
One-time license
Future Updates
This purchase includes the current version of the skill. If you want future adapter updates — meaning compatibility and packaging updates as supported platforms evolve — plus new catalog additions included automatically, upgrade to Pro.