aquavis12/power-aws-inventory
A Kiro Power that scans your AWS account and generates comprehensive infrastructure inventory reports in Excel format — 109 service categories, multi-region, fully formatted.
stack: Python
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~11.7k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add aws-mcp -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx mcp-proxy-for-aws==1.6.0 https://aws-mcp.us-east-1.api.aws/mcp --read-only --metadata AWS_REGION=us-east-1 $ claude mcp add aws-documentation-mcp-server -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx awslabs.aws-documentation-mcp-server==1.2.0 $ claude mcp add awsiac -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx awslabs.aws-iac-mcp-server==1.0.26 $ claude mcp add --transport http awsknowledge https://knowledge-mcp.global.api.aws $ claude mcp add awspricing -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx awslabs.aws-pricing-mcp-server==1.1.1 $ npx degit aquavis12/power-aws-inventory/skills ./rig-power-aws-inventory/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add aws-mcp -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx mcp-proxy-for-aws==1.6.0 https://aws-mcp.us-east-1.api.aws/mcp --read-only --metadata AWS_REGION=us-east-1 $ claude mcp add aws-documentation-mcp-server -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx awslabs.aws-documentation-mcp-server==1.2.0 $ claude mcp add awsiac -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx awslabs.aws-iac-mcp-server==1.0.26 $ claude mcp add --transport http awsknowledge https://knowledge-mcp.global.api.aws $ claude mcp add awspricing -e FASTMCP_LOG_LEVEL=YOUR_FASTMCP_LOG_LEVEL -- uvx awslabs.aws-pricing-mcp-server==1.1.1
$ npx degit aquavis12/power-aws-inventory/skills/diagram .claude/skills/diagram $ npx degit aquavis12/power-aws-inventory/skills/inventory .claude/skills/inventory
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (5)
| server | source | est. tokens |
|---|---|---|
| mcp-proxy-for-aws · "aws-mcp" env: FASTMCP_LOG_LEVEL | pypi | 2.5k |
| AWS Documentation · "aws-documentation-mcp-server" env: FASTMCP_LOG_LEVEL | pypi | 1.5k |
| awslabs.aws-iac-mcp-server · "awsiac" env: FASTMCP_LOG_LEVEL | pypi | 2.5k |
| knowledge-mcp.global.api.aws · "awsknowledge" | remote · remote | 2.5k |
| awslabs.aws-pricing-mcp-server · "awspricing" env: FASTMCP_LOG_LEVEL | pypi | 2.5k |
Skills (2)
Similar rigs
aquavis12/power-aws-resilience-hub
Kiro Power for AWS Resilience Hub + Amazon ARC — GenAI failure-mode assessments, RTO/RPO validation, failover orchestration, and cost-quantified remediation reports, from the IDE.
Pragmatist 9.3k tok · · Q0
aws-samples/sample-aws-genai-ops-demos
Deployable code samples demonstrating how generative AI transforms cloud operations. Deploy as-is with one click, or adapt to your specific environment with minimal customization effort.
Pragmatist 17.7k tok · · Q17
klang/claude-bedrock-setup
Quick and dirty way to set up Claude Code to use Bedrock as backend
Pragmatist 7.7k tok · · Q15
farinazgh/kiro-agentic-dev-labs
💜👻💜 Hands-on exploration of AWS Kiro: spec-driven development, multi-agent orchestration, steering files, reusable agent skills, hooks, MCP integrations, and AI-assisted software engineering using Java and Spring Boot.
Pragmatist 7.4k tok · · Q0