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 skills add borhen68/SkillEngine --skill cost-optimizationgit clone --depth 1 https://github.com/borhen68/SkillEngineWrote 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/borhen68/skillengine/cost-optimization)<a href="https://agentmods.dev/skills/borhen68/skillengine/cost-optimization"><img src="https://agentmods.dev/badge/skills/borhen68/skillengine/cost-optimization/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/skills/borhen68/skillengine/cost-optimization"><img src="https://agentmods.dev/badge/skills/borhen68/skillengine/cost-optimization.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 | $0.00052 | $0.02423 |
| Opus 5.5 | $0.00021 | $0.00969 |
| Sonnet 5.5 | $0.00010 | $0.00485 |
| Haiku 4.5 | $0.00005 | $0.00242 |
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 1mo 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Optimization
Overview
Cost optimization is not about being cheap — it's about spending money where it creates value and eliminating waste. In cloud environments, costs compound silently: oversized instances, forgotten dev environments, unoptimized storage tiers, and data transfer charges that nobody tracks. This skill provides a systematic approach to finding and eliminating waste while maintaining (or improving) system reliability.
The 80/20 rule of cloud costs: 80% of your bill comes from 20% of your resources. Focus on the big items first.
When to Use
- Monthly cloud bill has grown > 20% without corresponding traffic growth
- Setting up new infrastructure and want cost-aware defaults
- Reviewing architecture for a system that's been running > 6 months
- Preparing for scaling events (launch, Black Friday, viral growth)
- Evaluating multi-cloud vs single-cloud strategies
- After an audit reveals "surprise" charges (data transfer, API calls, storage)
NOT for:
- Systems where reliability is worth any cost (life-critical, financial trading)
- One-time cost reduction without ongoing monitoring (costs creep back)
The Cost Optimization Process
Step 1: Measure and Allocate
You can't optimize what you can't measure. Before changing anything:
COST ALLOCATION FRAMEWORK:
├── Tag everything (owner, environment, product, cost-center)
├── Enable detailed billing exports (hourly granularity)
├── Set up cost anomaly detection
├── Allocate shared costs (network, monitoring, platform)
└── Create per-team visibility dashboards
Key metrics to track:
| Metric | Why It Matters | Target |
|---|---|---|
| Cost per request | Efficiency of serving traffic | Trending down |
| Cost per user | Unit economics | Trending down |
| Idle resource % | Waste identification | < 10% |
| Storage $/GB | Tier optimization | Match workload pattern |
| Data transfer | Often the "surprise" line item | < 10% of total |
Step 2: Identify Waste
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.
- 1mo ago First seen · 301 lines · 52 tokens per session scan A 086d3b1087d3
cost-optimization is a skill published in the GitHub repository borhen68/SkillEngine (17 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 2,423 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
code-review-and-quality
A code-review guide for checking changes across correctness, readability, architecture, security, and performance before they are merged.
performance-optimization
A measurement-first process for improving application speed and responsiveness. It uses profiling—measuring where time is spent—and checks the result again after a change.
constraint-driven-development
A development method for writing a project's quality standards as a lasting, checkable contract. It can cover areas such as test coverage, security, performance, accessibility, and architecture.
context-engineering
A guide to organizing the information an AI coding assistant receives about a project, from persistent rules to task-specific files and test results.
doubt-driven-development
A development practice that puts an independent, fresh-context challenge in front of important coding decisions.