aws-cost-budgets-specialist
Skill0 starsChanged 46 days agoMITView on GitHub
AWS Budgets setup for cost or usage ceilings
In this repository146 other files it gives its agents.
- accessibility-compliance-enforcerSkill
- ai-anthropic-api-specialistSkill
- ai-anthropic-claude-runtime-env-guruSkill
- ai-avatar-presenter-specialistSkill
- ai-aws-bedrock-agentcore-guruSkill
- ai-aws-bedrock-agents-guruSkill
- ai-aws-bedrock-specialistSkill
- ai-aws-sagemaker-specialistSkill
- ai-context-masterSkill
- ai-llm-datasets-specialistSkill
- ai-powered-personalization-engineSkill
- ai-video-editor-postproduction-guruSkill
- ai-video-generation-orchestratorSkill
- ai-voice-audio-production-guruSkill
- ai-voice-dubbing-orchestratorSkill
- android-ndk-coderSkill
- apac-market-specialistSkill
- app-store-optimization-specialistSkill
- aptos-react-next-wallet-integrationSkill
- aptos-ts-sdk-coreSkill
- authjs-specialistSkill
- aws-console-cli-agentSkill
- aws-ec2-lambda-s3-specialistSkill
- aws-eks-specialistSkill
- aws-iam-guruSkill
- base-erc4337-paymaster-sponsorshipSkill
- base-react-next-wallet-integrationSkill
- business-viral-adoption-acceleratorSkill
- ci-cd-pipeline-specialistSkill
- code-apple-pwa-ios-16-guruSkill
- codebase-memory-mcpSkill
- competitive-intelligence-analystSkill
- competitive-intelligence-specialistSkill
- crisis-communication-reputation-managerSkill
- cross-border-legal-compliance-specialistSkill
- cursor-agents-orchestration-guruSkill
- cursor-hooks-automation-guruSkill
- cursor-installer-engineerSkill
- cursor-marketplace-publisher-guruSkill
- cursor-mcp-plugin-integration-specialistSkill
- cursor-plugin-architect-guruSkill
- cursor-sdk-automation-guruSkill
- cursor-skills-rules-author-guruSkill
- cybersecurity-governance-specialistSkill
- dagi-general-expertSkill
- developer-experience-architectSkill
- devops-aptos-gas-station-opsSkill
- devops-auto-repair-shop-crm-guruSkill
- devops-base-paymaster-opsSkill
- devops-ffmpeg-live-transmux-hls-packaging-guruSkill
- devops-hetzner-api-specialistSkill
- devops-k8s-dns-cluster-guruSkill
- devops-k8s-forgejo-guruSkill
- devops-k8s-guruSkill
- devops-k8s-local-storage-guruSkill
- devops-k8s-mail-addons-guruSkill
- devops-k8s-nginx-guruSkill
- devops-k8s-rook-ceph-guruSkill
- devops-k8s-tailscale-tunnelSkill
- devops-k8s-valero-backupSkill
- The first 60 shown.
The file
Files
AWS Cost Budgets Specialist
Summary
Ringdom AWS FinOps truth: promotional and Free Tier credits ($100 on signup plus up to $100 for Explore AWS activities; Free plan ends at six months or credit exhaustion) disappear under Bedrock on-demand tokens, cache writes, and Priority tier latency premiums unless AWS Budgets track both ACTUAL and FORECASTED cost/usage with SNS+email. Budget Actions (APPLY_IAM_POLICY Deny on bedrock:Invoke*, ec2:RunInstances, etc.; org APPLY_SCP_POLICY from management account; RUN_SSM_DOCUMENTS to stop EC2/RDS) are the hard ceiling—alerts alone are insufficient. Cost Explorer UI is free; Cost Explorer API is $0.01/request; first enablement needs ~24h for current month. First two action-enabled budgets/account/month are free; extra action budgets cost $0.10/day; action-less budgets are free. Cost Anomaly Detection catches Bedrock spikes budgets miss between refresh windows. Always Free monthly allowances still apply after credits; short-term trials activate on first use. Tag every Ringdom experiment with cost allocation tags before launch; filter Cost Explorer by service=Amazon Bedrock and by tag. Pair with aws-console-cli-agent for CLI/IAM wiring and ai-aws-bedrock-specialist for model/tier choice—this lens owns spend caps, not model quality.
Instructions
- Pattern: create monthly COST budget with fixed target at remaining credit runway -> alert at 50/80/90% ACTUAL and 80/100% FORECASTED before burn-through.
- Pattern: attach Budget Action APPLY_IAM_POLICY Deny on bedrock:InvokeModel* + related inference APIs at 90% ACTUAL -> hard stop new inference without deleting data.
- Pattern: create USAGE budget filtered to Amazon Bedrock (or specific usage types) -> catch token volume before dollar threshold if unit prices change.
- Pattern: enable Cost Explorer once, wait ~24h, group by Service then filter Bedrock + group by tag:Project -> allocate experiment burn to owners.
- Pattern: activate Free Tier credit page + Budgets excluding/including credits intentionally -> know whether alert tracks cash or credit-adjusted spend.
- Pattern: Cost Anomaly Detection monitor on linked account / service Bedrock with SNS -> catch intra-day spikes Budgets lag cannot see.
- Pattern: require ActivateCostAllocationTags for Environment, Project, Owner, Workload -> reject untagged creates via IAM Condition aws:RequestTag.
- Pattern: org management account APPLY_SCP_POLICY Deny expensive services on member experiment OU at threshold -> blast-radius fence for clones.
- Pattern: prefer Bedrock Flex/Batch and prompt cache reads over Priority tier for non-latency work -> extend credit runway without code rewrite.
- Pattern: emergency kill: attach Deny policy + stop SSM on EC2/RDS + disable model access in Bedrock console/CLI -> document revert path before auto-approve.
- Pattern: first two action-enabled budgets free; keep kill-switch budgets action-enabled and analytics budgets action-less -> control Budgets line-item cost.
- Pattern: reconcile CUR 2.0 Bedrock lines for input/output/cache-read/cache-write -> avoid undercount when prompt caching is on.
Deeper fields
jq -r '.mission, .expertise, .keywords' "mcp/AI-LEGIOX/legiox-truth-lens/aws-cost-budgets-specialist.nodus.json"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

