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 vasilyu1983/AI-Agents-public --skill ops-cost-optimizationgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/ops-cost-optimization)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ops-cost-optimization"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ops-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/vasilyu1983/ai-agents-public/ops-cost-optimization"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ops-cost-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.03345 |
| Opus 5.5 | $0.00020 | $0.01338 |
| Sonnet 5.5 | $0.00010 | $0.00669 |
| Haiku 4.5 | $0.00005 | $0.00334 |
Grade A, and why
ops-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 22d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaaS/PaaS Cost Optimization
Use this skill to audit, reduce, and monitor infrastructure and SaaS spending. Keep the output operational: cost breakdown, waste identification, optimization actions, and monitoring setup.
Quick Reference
| Need | Starting Reference | Notes |
|---|---|---|
| audit a SaaS or infrastructure vendor bill (Vercel, Supabase, Cloudflare, Stripe, GitHub/CI, monitoring, email, domains) | references/vendor-billing-guide.md | vendor lookup step, plan-tier crossover, per-vendor billing dimensions and ranked levers |
| audit payment processing | references/vendor-billing-guide.md#stripe | stacked-fee arithmetic, IC+ rule, payment mix, Radar break-even, volume negotiation |
| audit AI API spend or self-host vs API breakeven | references/ai-api-cost-guide.md | cost-per-success model, prompt caching, batch API, model routing, breakeven formula |
| quantify uncertain cost or budget risk | references/cost-uncertainty-method.md | reproducible Monte Carlo, joint empirical dependence, Morris screening |
| decide on AWS/GCP/Azure commitments or K8s cost allocation | references/cloud-commitment-and-k8s-cost-guide.md | d-quantile commitment sizing, instrument shapes (Savings Plans, RIs, CUDs, Spot), application order, exit rules per provider, when NOT to commit, showback before chargeback, GPU capacity, FinOps Framework vocabulary |
| cut egress or storage-class cost | references/cloud-commitment-and-k8s-cost-guide.md#egress-and-storage-class-traps | cross-AZ and NAT charges, minimum storage duration, retrieval and rehydration, small-object minimums, break-even before a lifecycle rule |
| set up cost monitoring | references/cost-monitoring-setup.md | budget alerts, review cadence, FOCUS normalization |
| track unit economics | references/unit-economics-guide.md | cost per customer/feature/request, ARPC tracking, FOCUS standard |
| IaC cost guardrails in CI | references/vendor-billing-guide.md#iac-cost-guardrails | Infracost PR diffs, budget-threshold merge gates |
| monthly cost review | assets/monthly-cost-review-checklist.md | reusable review template |
| automated cost audit from billing data | agents/cost-auditor.md | parses screenshots/API data, ranks top 5 cost drivers, outputs prioritized actions |
What ships with it
18 files 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.
- agents/cost-auditor.md 2.8 KB
- agents/openai.yaml 370 B
- assets/cost-uncertainty-example.json 3.3 KB
- assets/cost-uncertainty-joint-example.json 1012 B
- assets/monthly-cost-review-checklist.md 2.1 KB
- data/sources.json 13 KB
- learnings.consolidated.md 597 B
- learnings.md 580 B
- references/ai-api-cost-guide.md 23 KB
- references/cloud-commitment-and-k8s-cost-guide.md 32 KB
- references/cost-monitoring-setup.md 8.3 KB
- references/cost-uncertainty-method.md 3.9 KB
- references/unit-economics-guide.md 11 KB
- references/vendor-billing-guide.md 33 KB
- scripts/cost_estimator.py 10 KB runs code
- scripts/cost_uncertainty.py 27 KB runs code
- scripts/test_cost_estimator.py 8.6 KB runs code
- scripts/test_cost_uncertainty.py 15 KB runs code
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.
- 22d ago Changed · -25 lines cac6895b2f93
- 1mo ago Changed · +10 lines cc8890b09e40
- 1mo ago First seen · 192 lines · 49 tokens per session scan A 97436a983fad
ops-cost-optimization is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (101 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 3,345 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 2026-09-03.
Other skills, from other repositories
relay-deploy
Set up a complete deployment configuration — Dockerfile, deployment manifest, environment config, and rollback procedure. Use when asked about "deployment setup", "how do I deploy this", "deployment strategy", or "rollback plan".
linkerd-patterns
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
gitlab-ci-patterns
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
hybrid-cloud-networking
Configure secure, high-performance connectivity between on-premises infrastructure and cloud platforms using VPN and dedicated connections. Use when building hybrid cloud architectures, connecting data centers to cloud, or implementing secure cross-premises networking.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.