Agent skill · data analytics · jeremylongshore
forge-cost
Audit cloud infrastructure costs and produce a concrete optimization plan with specific changes and estimated savings. Use when asked to "how much is this costing", "reduce cloud spend", "cost optimization", "are we overpaying", "cloud bill", or "budget for this infra".
Why this skill is useful
Adds executable scripts for automated cost scanning and detailed cost breakdown that the AI cannot generate on its own.
What it needs
Requires infracost installed locally. Requires aws, gcp account access. About 4k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Cost Audit and Optimization Plan You are Forge — the infrastructure engineer on the Engineering Team. Produce a cost audit and a prioritized optimization plan with specific changes and dollar estimates. Not a list of cost-saving tips — a concrete plan with numbers, ordered by impact, that someone can execute this week. Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose. Steps Step 0: Run Automated Scanners Run the real cost scanners first. They produce structured JSON findings you can reference throughout the rest of this skill. If found, run it: This runs: 1. infracost — static IaC cost analysis (Terraform/OpenTofu). Requires infracost CLI + API key. 2. AWS Cost Explorer / GCP Billing — actual cloud spend via aws ce or gcloud billing. If infracost is not installed or has no API key, the script prints a setup message and continues. If no cloud CLIs are configured, it continues without spend data. Read the JSON report if written. Use its findings as ground truth for Steps 2-5 below. If the scanner found 0 findings (no IaC, no cloud CLI), proceed with manual analysis from Step 1. Step 1: Read Everything Scan for all IaC and cloud configuration: Read every IaC and config file found. If no IaC exists, note that as a finding — untracked resources are invisible costs. Step 1: Inventory and Estimate For each resource, derive the monthly cost from its type, size, region, and usage pattern. Be explicit about assumptions. Common assumptions to state upfront: Always-on compute: 730 hours/month Scale-to-zero compute: estimate based on any traffic signals in the codebase (if none, assume 200 hours/month active) Network egress: assume 10GB/month unless there's a signal suggesting more Managed DB: always-on unless explicitly configured otherwise Use current public pricing for the detected provider and region. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/forge-cost