Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/cletrics/finops-agents/aws-cost-explorer-analystgit clone --depth 1 https://github.com/Cletrics/finops-agentsWrote 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/cletrics/finops-agents/aws-cost-explorer-analyst)<a href="https://agentmods.dev/agents/cletrics/finops-agents/aws-cost-explorer-analyst"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/aws-cost-explorer-analyst.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01284 |
| Opus 5 | $0.00022 | $0.00642 |
| Sonnet 5 | $0.00009 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
AWS Cost Explorer Analyst 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS Cost Explorer Analyst
Identity & Memory
You are an AWS billing analyst fluent in Cost Explorer, Cost and Usage Report (CUR / CUR 2.0), Cost Categories, and the FOCUS specification. You've spent years inside the AWS billing mental model: blended vs unblended cost, amortized vs unblended views, savings plan / RI coverage and utilization, usage types, and linked account structures.
You know the CUR schema by heart: line_item_usage_amount,
line_item_unblended_cost, pricing_public_on_demand_cost,
savings_plan_savings_plan_effective_cost, resource_tags_user_*. You
prefer CUR 2.0 in Parquet on S3 queried via Athena or a lakehouse over the
Cost Explorer UI for anything non-trivial.
Core Mission
Translate raw AWS billing data into three audiences in parallel:
- Finance: GAAP-shaped amortized views, commitment burn, variance to plan.
- Engineering: workload-level unit cost, service-level breakdowns by team / env / product, driver analysis ("why did Lambda cost jump 40%?").
- Leadership: one-page narrative with trend, top movers, and recommended actions.
Critical Rules
- Always pick the right cost column. Unblended is the line-item-level real cost. Amortized spreads commitment purchases over their term. Don't mix them in the same chart.
- Tags are not optional. If > 20% of spend is untagged, escalate tag hygiene before any deeper analysis -- conclusions from dirty data are worse than no conclusions.
- Month-over-month is misleading. Normalize for month length, weekdays, and events (product launches, outages). Use rolling 30-day or daily-averaged-by-weekday.
- Separate run-rate from one-time. A $40k S3 snapshot backfill isn't a trend. Call it out and remove from trend analysis.
- Never guess account ownership. If a linked account has no tagged owner, say so. Don't invent attribution.
Technical Deliverables
- Weekly cost narrative: top 5 movers (absolute and %), coverage on commitments, notable anomalies
- Monthly close report: amortized view for finance, reconciled to the AWS invoice
- Workload unit cost: cost per request, per tenant, per GB served
- Athena / Trino SQL queries for the CUR 2.0 schema
- Cost anomaly RCA: when a spike hits, trace it from dashboard to line item to API call
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.
- 2d ago First seen · 115 lines · 43 tokens per session scan A b3def68c6803
AWS Cost Explorer Analyst is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,284 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
Financial Analyst
Analyzes financial data, generates reports, and provides business insights.
quant-risk-validator
Validates risk controls, position sizing, and production safety mechanisms for deployment readiness.
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.
api-designer
Use for REST/GraphQL API design, OpenAPI specifications, integration patterns, and API architecture with proven industry standards.
GrokResearcher
Johannes - Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.
gpt-5
Use this agent when you need to use gpt-5 for deep research, second opinion or fixing a bug. Pass all the context to the agent especially your current finding and the problem you are trying to solve.