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 joao-aires/agent-skills-public --skill optimize-application-costgit clone --depth 1 https://github.com/joao-aires/agent-skills-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/joao-aires/agent-skills-public/optimize-application-cost)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/optimize-application-cost"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/optimize-application-cost/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/joao-aires/agent-skills-public/optimize-application-cost"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/optimize-application-cost.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 | $0.00049 | $0.00888 |
| Opus 5.5 | $0.00020 | $0.00355 |
| Sonnet 5.5 | $0.00010 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
optimize-application-cost 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize application cost
Read composition guidance for optional expertise, fallback and scope.
Attribute the real bill
Identify the environment, provider, region, currency, billing period and application/team ownership.
- Use current invoices, price sheets and usage where available; separate estimates from billed amounts and allocated cost from cash savings.
- Use EUR and relevant European regions for this user's estimates unless the project specifies otherwise.
- Keep exchange-rate date, taxes/discount assumptions and commitments explicit; do not invent price conversions or reuse stale rates.
Trace the bill to the work the application performs and the capacity kept available for it. Include compute, databases, storage/backup retention, network egress and load balancers, logs/telemetry, build artifacts, CI minutes and third-party/AI usage. Keep shared system costs and idle capacity visible, and state how shared amounts are allocated so apparent savings do not merely move to another owner.
Track total spend alongside a useful unit such as cost per active user, completed job or request. Use completed useful work as the denominator when retries or failed operations can consume significant resources. Separate a more efficient unit cost from a reduction in the bill: growth, fixed commitments and unused reserved capacity can make those outcomes differ.
Optimize against constraints
Read capacity, recovery, latency and privacy requirements before proposing savings.
Prioritize unused resources, oversized allocations, unnecessary data movement/retention and expensive hot paths. Compare relevant levers against their constraints:
| Lever | Constraint or evidence needed |
|---|---|
| Kubernetes requests/capacity | Compare representative actual usage, node packing and scheduling constraints. Establish whether released capacity reduces billable nodes; lower pod requests alone do not prove savings. |
| Managed database/storage sizing | Preserve backup needs, restore coverage and resilience. |
| Interruptible/spot capacity | The workload tolerates interruption. |
| Commitments/reservations | Stable demand and a break-even assessment; a published discount alone is insufficient. |
| Scaling to zero | Acceptable startup latency and supported infrastructure. |
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 Changed · +14 lines 3e0bb16d3a16
- 2d ago Changed · +2 lines fbc4ed89ecea
- 7d ago Changed · +3 lines 2101e7fb7c3c
- 10d ago Changed · +6 lines d81c3ce97927
- 11d ago First seen · 37 lines · 49 tokens per session scan A dc7663a18b77
optimize-application-cost is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 888 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 2026-10-11.
Other skills, from other repositories
aws-cost-operations
AWS cost optimization, monitoring, and operational excellence expert. Use when analyzing AWS bills, estimating costs, setting up CloudWatch alarms, querying logs, auditing CloudTrail activity, or assessing security posture.
aws-cost-cleanup
Automated cleanup of unused AWS resources to reduce costs.
azure-compute
Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev/test, workload, family, load balancer, Flexible orchestration, Uniform orchestration, cost…
azure-cost
Azure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: "Azure costs", "Azure bill", "cost breakdown", "how much am I spending", "forecast spending", "optimize costs", "reduce spending", "orphaned resources", "rightsize VMs", "cost spike", "reduce storage costs", "AKS cost". DO NOT USE…
cost-estimation
Forecast Azure spend and price planned resources or workloads. WHEN: "forecast Azure spending", "project next month cost", "compare forecast to my planning target", "how much will Azure cost", "estimate VM cost", "compare storage tiers", "compare Azure regions", "retail price", "EA rate card", "negotiated pricesheet".…
cost-governance
Govern Azure costs with budgets, alerts, tags, and policy restrictions. WHEN: "Azure budget health", "configured budget overrun", "list Azure budgets", "create Azure budget", "budget alerts", "budget coverage", "missing CostCenter tags", "allowed VM SKUs", "allowed Azure regions", "would this SKU be denied", "cost…