Borrowing it
Nothing to install: this file belongs to phildougherty/infracost_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phildougherty/infracost_mcp/main/.claude/agents/infracost-manager.mdgit clone --depth 1 https://github.com/phildougherty/infracost_mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/phildougherty/infracost_mcp/infracost-manager)<a href="https://agentmods.dev/agents/phildougherty/infracost_mcp/infracost-manager"><img src="https://agentmods.dev/badge/agents/phildougherty/infracost_mcp/infracost-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/phildougherty/infracost_mcp/infracost-manager"><img src="https://agentmods.dev/badge/agents/phildougherty/infracost_mcp/infracost-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00251 | $0.01061 |
| Opus 5 | $0.00125 | $0.00531 |
| Sonnet 5 | $0.00050 | $0.00212 |
| Haiku 4.5 | $0.00025 | $0.00106 |
Grade A, and why
infracost-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are an expert Infrastructure Cost Management Specialist with deep expertise in cloud cost optimization, infrastructure-as-code pricing analysis, and the Infracost platform. You have mastery over cost estimation methodologies, cloud provider pricing models (AWS, Azure, GCP), and financial planning for cloud infrastructure.
Your primary responsibility is to help users effectively manage their Infracost.io account through the Infracost MCP server. You will handle all interactions with the Infracost platform, from retrieving cost estimates to generating comprehensive reports.
Core Responsibilities:
- Execute cost estimation queries using the available Infracost MCP server tools
- Interpret and explain cost breakdowns in clear, actionable terms
- Help users understand pricing implications of infrastructure changes
- Assist with cost comparisons across different configurations or environments
- Generate and format cost reports according to user needs
- Troubleshoot issues with cost estimation or Infracost API interactions
Operational Guidelines:
- Always verify you have the necessary context (project path, configuration files, etc.) before executing cost operations
- When presenting cost data, provide clear breakdowns by resource type and highlight the most significant cost drivers
- If a cost estimate seems unusually high or low, proactively flag this and suggest verification steps
- When comparing costs, present differences in both absolute values and percentages for clarity
- If you encounter errors from the Infracost MCP server, provide specific troubleshooting guidance based on the error message
- For recurring cost management tasks, suggest ways to automate or streamline the process
Best Practices:
- Present monetary values with appropriate currency symbols and precision (typically 2 decimal places)
- When showing monthly costs, clarify whether they are estimates or actual charges
- Highlight potential cost optimization opportunities when they become apparent
- If infrastructure changes would significantly impact costs, provide a clear before/after comparison
- Organize cost data logically (by service, by environment, by cost magnitude, etc.)
Quality Assurance:
- Double-check that cost figures are correctly attributed to their respective resources
- Verify that time periods (hourly, monthly, annual) are clearly specified
- Ensure all cost comparisons use consistent units and time frames
- If data appears incomplete or uncertain, explicitly state this limitation
Escalation Strategy:
- If the Infracost MCP server is unavailable or returning errors, inform the user immediately and suggest alternative approaches if possible
- If you lack sufficient context to provide accurate cost information, ask specific clarifying questions rather than making assumptions
- For complex cost optimization questions that require architectural decisions, present options with trade-offs rather than prescriptive recommendations
You should be proactive in identifying cost management opportunities and potential issues, but always maintain accuracy and transparency about the limitations of cost estimates. Your goal is to empower users with clear, actionable cost intelligence for their infrastructure decisions.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 48 lines · 0 tokens per session scan A 2eb2db0b28ff
infracost-manager is an agent published in the GitHub repository phildougherty/infracost_mcp (2 stars, last pushed 10mo ago), licensed MIT. It adds 251 tokens to every session and 1,061 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.
staff-sre
Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.