| name | aws-pricing |
| description | Use when working with Aws Pricing — aWS pricing helper for cost queries.
ALWAYS use get_aws_cost script for pricing questions. Use when: - User asks
about AWS resource costs or pricing - User wants to compare pricing across
regions - User needs spot, on-demand, or reserved pricing info Triggers: aws
pricing, aws cost, how much does, ec2 price, rds cost, s3 pricing.
|
| connection_type | aws |
| preload | false |
AWS Pricing Helper
MANDATORY RULE: Always answer pricing questions with the get_aws_cost helper. NEVER call external search tools or guess prices.
The helper script get_pricing_aws.sh lives in the sandbox skills directory.
You must source it before use:
source ./_skills/connections/aws/aws-pricing/scripts/get_pricing_aws.sh
Run get_aws_cost without stderr redirection or grep filtering so the agent receives the raw response.
If multiple pricing lookups are required, place every call in a single Bash script (one script per task).
Usage
source ./_skills/connections/aws/aws-pricing/scripts/get_pricing_aws.sh
get_aws_cost <resource> <region> [options]
Supported Resources
| Category | Resources |
|---|
| EC2 | t3.micro, m5.large, g4dn.xlarge, c6i.large |
| RDS | db.t3.micro, db.r5.large |
| ElastiCache | cache.t3.micro, cache.r5.large |
| S3 | s3-standard, s3-ia, s3-glacier, s3-glacier-deep |
| Lambda | lambda-128mb, lambda-1gb, lambda-3gb |
| DynamoDB | dynamodb-ondemand, dynamodb-provisioned |
| EFS | efs-standard, efs-ia |
| EBS | gp3-100gb, io2-500gb, st1-1tb |
| CloudFront | cloudfront-standard |
| API Gateway | apigateway-rest, apigateway-http |
| SQS | sqs-standard, sqs-fifo |
| SNS | sns-standard |
| Route53 | route53-hosted-zone, route53-query |
| ALB | alb-standard |
| NAT Gateway | natgw-standard |
| VPC Endpoints | vpce-gateway, vpce-interface |
Parameters
resource: Auto-detected from the naming pattern aboveregion: AWS location string (e.g., "Asia Pacific (Singapore)", "US East (N. Virginia)")options: --spot (include spot pricing), --detailed (verbose output), --no-reserved (skip reserved pricing)
Examples
get_aws_cost t3.micro "US East (N. Virginia)" --spot
get_aws_cost db.t3.micro "Asia Pacific (Singapore)"
get_aws_cost s3-standard "US East (N. Virginia)"
get_aws_cost lambda-1gb "US East (N. Virginia)"
get_aws_cost cloudfront-standard "US East (N. Virginia)"
get_aws_cost apigateway-rest "US East (N. Virginia)"
get_aws_cost sqs-standard "US East (N. Virginia)"
Output
Human-readable pricing data with service details, region, specs, on-demand, reserved, and spot pricing where available.
If a resource is unsupported, the helper prints guidance for querying the AWS Pricing API manually.
Output Format
Present results as a structured report:
Aws Pricing Report
══════════════════
Resources discovered: [count]
Resource Status Key Metric Issues
──────────────────────────────────────────────
[name] [ok/warn] [value] [findings]
Summary: [total] resources | [ok] healthy | [warn] warnings | [crit] critical
Action Items: [list of prioritized findings]
Target ≤50 lines of output. Use tables for multi-resource comparisons.
Anti-Hallucination Rules
- NEVER assume resource names — always discover via CLI/API in Phase 1 before referencing in Phase 2.
- NEVER fabricate metric names or dimensions — verify against the service documentation or
--help output.
- NEVER mix CLI commands between service versions — confirm which version/API you are targeting.
- ALWAYS use the discovery → verify → analyze chain — every resource referenced must have been discovered first.
- ALWAYS handle empty results gracefully — an empty response is valid data, not an error to retry.
Counter-Rationalizations
| Shortcut | Counter | Why |
|---|
| "I'll skip discovery and check known resources" | Always run Phase 1 discovery first | Resource names change, new resources appear — assumed names cause errors |
| "The user only asked for a quick check" | Follow the full discovery → analysis flow | Quick checks miss critical issues; structured analysis catches silent failures |
| "Default configuration is probably fine" | Audit configuration explicitly | Defaults often leave logging, security, and optimization features disabled |
| "Metrics aren't needed for this" | Always check relevant metrics when available | API/CLI responses show current state; metrics reveal trends and intermittent issues |
| "I don't have access to that" | Try the command and report the actual error | Assumed permission failures prevent useful investigation; actual errors are informative |
