Analyze costs

Skill harness/harness-skills/skills/analyze-costs

A collection of structured AI agent skills that enable Claude Code, Cursor, GitHub Copilot, and other AI coding assistants to create, operate, debug, and govern Harness CI/CD workflows through natural language.

Install

npx -y skills add harness/harness-skills --skill analyze-costs

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Analyze cloud costs, find optimization opportunities, and track anomalies using Harness CCM via MCP. Use when user says "cloud costs", "analyze costs", "cost optimization", "reduce spending", "cost report", or asks about cloud bills.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.7 KB, as published. Nobody here has run it

Analyze Costs

Analyze cloud costs and identify savings using Harness Cloud Cost Management (CCM) via MCP.

Instructions

Step 1: Get Cost Overview

Call MCP tool: harness_get
Parameters:
  resource_type: "cost_account_overview"

Returns total spend, provider breakdown, and trend vs previous period.

Step 2: Get Cost Breakdown

Call MCP tool: harness_get
Parameters:
  resource_type: "cost_breakdown"

Multi-dimensional breakdown by service, environment, team, region.

Step 3: Explore Perspectives

Call MCP tool: harness_list
Parameters:
  resource_type: "cost_perspective"

Then get detailed data for a specific perspective:

Call MCP tool: harness_get
Parameters:
  resource_type: "cost_perspective"
  resource_id: "<perspective_id>"

Step 4: Get Cost Trends

Call MCP tool: harness_get
Parameters:
  resource_type: "cost_timeseries"

Step 5: Get Optimization Recommendations

Call MCP tool: harness_list
Parameters:
  resource_type: "cost_recommendation"

For detailed recommendation info:

Call MCP tool: harness_get
Parameters:
  resource_type: "cost_recommendation_detail"
  resource_id: "<recommendation_id>"

Summary statistics:

Call MCP tool: harness_get
Parameters:
  resource_type: "cost_recommendation_stats"

Step 6: Check for Anomalies

Call MCP tool: harness_list
Parameters:
  resource_type: "cost_anomaly"

To dismiss a known anomaly:

Call MCP tool: harness_execute
Parameters:
  resource_type: "cost_anomaly"
  action: "report_feedback"
  resource_id: "<anomaly_id>"
  body: { feedback: "FALSE_ANOMALY" }  # or TRUE_ANOMALY / NOT_RESPONDED

Step 7: Commitment Analysis

Call MCP tool: harness_get
Parameters:
  resource_type: "cost_commitment"

Report Format

## Cloud Cost Analysis

**Period:** Last 30 Days

### Summary
| Provider | Spend | vs Previous |
|----------|-------|-------------|
| AWS      | $X    | +X%         |
| GCP      | $X    | +X%         |
| Azure    | $X    | -X%         |

### Top Recommendations
1. **Rightsize <resource>** - Save $X/month (95% confidence)
2. **Convert to Reserved** - Save $X/month
3. **Delete unused resources** - Save $X/month

### Anomalies
- <date>: <service> spiked $X above expected

### Actions
- [ ] Rightsize instance X
- [ ] Purchase reserved capacity
- [ ] Clean up unused volumes

Cost Resource Types Reference

Resource Type	Operations	Description
`cost_account_overview`	get	Account-level total spend summary
`cost_summary`	get	Perspective-scoped cost summary
`cost_timeseries`	get	Cost trends over time
`cost_breakdown`	get	Multi-dimensional breakdown
`cost_perspective`	list, get	Custom cost views
`cost_recommendation`	list	Optimization suggestions
`cost_recommendation_detail`	get	Detailed recommendation
`cost_recommendation_stats`	get	Summary statistics
`cost_anomaly`	list, get, execute(report_feedback)	Cost spikes
`cost_anomaly_summary`	get	Anomaly aggregate summary
`cost_category`	list, get	Cost allocation
`cost_commitment`	get	Commitment coverage/utilisation/savings
`cost_filter_value`	get	Available filter values

Examples

"How much are we spending on cloud?" - Get cost_account_overview
"Find $5,000 in monthly savings" - List cost_recommendations, prioritize by savings
"Why did our bill spike last week?" - List cost_anomaly
"Break down costs by team" - Get cost_breakdown or cost_perspective
"Are we using our reserved instances?" - Get cost_commitment

Performance Notes

Gather data from all relevant perspectives before drawing cost conclusions. Partial data leads to incorrect recommendations.
Cross-reference recommendations with anomaly data to distinguish trends from spikes.
Quality of cost analysis is more important than speed. Verify savings estimates before presenting.