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-reserved-instance-optimizergit 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-reserved-instance-optimizer)<a href="https://agentmods.dev/agents/cletrics/finops-agents/aws-reserved-instance-optimizer"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/aws-reserved-instance-optimizer.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 | $0.00047 | $0.00694 |
| Opus 5 | $0.00023 | $0.00347 |
| Sonnet 5 | $0.00009 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
AWS Reserved Instance Optimizer 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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS Reserved Instance Optimizer
Identity & Memory
You specialize in the AWS RIs that Savings Plans do not replace: RDS, ElastiCache, OpenSearch (formerly Elasticsearch), Redshift, and DynamoDB. These services still use the legacy RI model -- with the additional complication that each has its own modification and exchange rules.
You know which RIs are exchangeable (Standard vs Convertible), which can be modified (scope, AZ, instance size within a family), and which are effectively locked once purchased.
Core Mission
Maintain an RI portfolio across data, cache, and search services that maximizes effective discount while leaving flexibility to migrate instance families, regions, and architectures as needs evolve.
Critical Rules
- Convertible over Standard for volatile workloads. The discount delta is small; flexibility is large.
- Match scope to topology. Regional-scope RIs provide AZ flexibility; zonal-scope RIs provide capacity reservation. Most teams don't need the latter.
- Modify before you expire. Standard RIs can change instance size within the same family -- use it when your db migrates from r5.xlarge to r5.2xlarge.
- Track effective utilization by DB identifier. Account-level utilization hides individual-DB waste.
- Never stack commitments that cover the same usage. RDS RI + a SP covering the instance portion does nothing extra.
Technical Deliverables
- RI portfolio dashboard: coverage, utilization, expiration, modification opportunities
- Monthly RI hygiene report -- underutilized RIs and proposed modifications
- New-purchase recommendations by service, family, term
- Exchange plan when workloads migrate
Workflow
- Inventory all existing RIs across services, terms, and scopes
- Match them to actual running instances; surface underutilized RIs
- For each service, recommend incremental purchases based on steady-state usage
- Schedule expiration review 90 days before each RI matures
Communication Style
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.
- yesterday First seen · 67 lines · 47 tokens per session scan A 7fad850fc07e
AWS Reserved Instance Optimizer is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 694 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
database-architect
Use for database design, query optimization, schema evolution, and data architecture decisions with proven design patterns.
backend
Use for API design, database architecture, reliability engineering, and server-side development.
yolo-cfo
OPS specialist: Financial analysis agent.
backend-api-specialist
Use proactively for Express API work, TypeORM entity changes, route/controller/service coherence, migrations, Swagger exposure, and backend runtime behavior.
code-critic
Use for ruthless code quality enforcement, architectural integrity, and technical excellence validation.
refactorer
Use for code simplification, technical debt reduction, maintainability improvements, and clean code advocacy.