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 skills/arjunprabhulal/devops-skills/cost-optimizationnpx skills add arjunprabhulal/devops-skills --skill cost-optimizationgit clone --depth 1 https://github.com/arjunprabhulal/devops-skillsWrote 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/skills/arjunprabhulal/devops-skills/cost-optimization)<a href="https://agentmods.dev/skills/arjunprabhulal/devops-skills/cost-optimization"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/cost-optimization.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 | $0.00123 | $0.01281 |
| Opus 5 | $0.00062 | $0.00641 |
| Sonnet 5 | $0.00025 | $0.00256 |
| Haiku 4.5 | $0.00012 | $0.00128 |
Grade A, and why
cost-optimization 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Optimization
Cloud bills rarely have one villain — they have a long tail of small waste and a short list of big levers. Teams that start by auditing every line item burn weeks on savings measured in dollars, while the resource that's 40% of the bill sits untouched because nobody sorted by size first. Optimization is a prioritization problem before it's an engineering problem.
The other trap is treating cost cutting as a one-time project. Spend drifts every time someone ships a new service, forgets to delete a test environment, or a traffic pattern shifts enough to make last quarter's instance sizes wrong. A cost review that runs once and declares victory is already stale by the next billing cycle.
Find the biggest lever with data, pull it, then come back for the next one.
For a ranked catalog of savings levers and how to find candidates, read
references/savings-levers.md.
1. Rank levers by dollar impact before touching anything
Sort the bill by service, then by resource, before deciding what to fix. A single oversized database instance can dwarf a dozen idle load balancers combined, and no amount of enthusiasm for cleaning up small things substitutes for finding the one thing that's actually expensive.
- Pull the billing export or cost-explorer report first — don't optimize from memory of what "feels" expensive.
- Work top-down — the top five line items usually explain most of the spend variance.
- Ignore anything under a threshold that isn't worth an engineer's time — a $20/month savings is not worth a change-review cycle.
Done when: the top five cost drivers are known by name and dollar amount, not by guess.
2. Kill idle and orphaned resources first — they buy nothing
An idle resource — a stopped-but-not-deleted instance, an unattached volume, a load balancer with no healthy targets, a snapshot nobody restores from — delivers zero value at full price. Unlike rightsizing or commitment purchases, removing it carries no performance trade-off to weigh, which makes it the fastest win available.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 108 lines · 123 tokens per session scan A 28a127f106b7
cost-optimization is a skill published in the GitHub repository arjunprabhulal/devops-skills (2 stars, last pushed 10d ago), licensed MIT. It adds 123 tokens to every session and 1,281 once invoked, about $0.0006 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 skills, from other repositories
google-cloud-recipe-onboarding
Guides a developer's first steps on Google Cloud, covering account creation, billing setup, project management, and deploying a first resource. Use when a new developer wants to initialize their first Google Cloud project, configure billing, and verify deployment. Don't use for enterprise organization setup (use…
google-ads-api-account-diagnostics
Diagnoses Google Ads account performance issues such as conversion loss (value or volume), low lead flow/volume, and lost impression share (opportunities) due to ad rank, bids, or budgets. Use when troubleshooting sudden performance drops, analyzing campaign impression share metrics, investigating low lead flow, or…
pier-cloud
This skill should be used when the user needs to consume the Pier Cloud (Lighthouse) API for cloud cost management — including JWT authentication, listing contexts, workspaces, and FinOps data views. Trigger whenever there is a need to integrate, automate, or debug calls to the Pier Cloud platform via Python, Node.js…
agent-platform-migrate-from-ai-studio
Guides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when moving applications to Google Cloud, to leverage Cloud credits, or to unify inferencing with other Cloud infrastructure (IAM, billing, telemetry).
cloud-finops
Expert FinOps guidance covering cloud, AI, SaaS, and adjacent technology spend. Includes AI cost management, GenAI capacity planning, AI-powered FinOps automation, Anthropic billing, AWS (EC2, Bedrock, Savings Plans, CUR, commitment strategy), Azure (reservations, Savings Plans, AHB, OpenAI PTUs, portfolio liquidity)…
context-memory
Persist and recall state between skill invocations. Store analysis results, trade setups, session context, and carry them across conversations.