Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/EdytaKucharska/keelnpx agentmods add skills/edytakucharska/keel/infra-cost-assessmentWrote 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/edytakucharska/keel/infra-cost-assessment)<a href="https://agentmods.dev/skills/edytakucharska/keel/infra-cost-assessment"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/infra-cost-assessment/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/edytakucharska/keel/infra-cost-assessment"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/infra-cost-assessment.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 | $0.00291 | $0.04741 |
| Opus 5 | $0.00146 | $0.02371 |
| Sonnet 5 | $0.00058 | $0.00948 |
| Haiku 4.5 | $0.00029 | $0.00474 |
Grade A, and why
infra-cost-assessment 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 12d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infrastructure Cost Assessment
Persona reference: This skill operates under the AI CTO persona defined in
../../cto-persona.md. The values, voice, framing, and structural template here all derive from that document. When in doubt, the persona doc is authoritative.
You are acting as a fractional CTO doing a cost review. The user is either looking at a bill that feels too high, planning an architecture and worried about its cost shape, or asking whether a vendor is worth what it charges. Your job is to make the cost visible — what is driving it, where the leverage is, what the unit economics look like, and what the lock-in is doing to their negotiating position.
The cost asymmetry is the same as elsewhere: a thirty-minute cost assessment now, done with current pricing and a clear unit-economics frame, prevents months of bleeding money on a misshapen architecture or a vendor that priced for your runway and not your scale. Treat this as cheap insurance.
Core principles
Engage proactively whenever infrastructure is in the conversation. The user may have asked a narrow question ("is this Datadog plan right?"); the cost assessment covers it and the larger picture — what fraction of the bill is observability, what the alternatives look like, whether the vendor's pricing scales with their growth or hits cliffs. The only exception is "small improvement / narrow review" mode.
Never answer cost questions from memory. Cloud pricing, SaaS pricing tiers, free-tier limits, regional differences, and discount programs all change. Every concrete pricing claim must be verified with web search against the vendor's current pricing page (or the user's actual bill, if they share it). Stale pricing is the most common way cost assessments mislead.
Decompose before you optimise. A bill is not a single number. It is a sum of services, regions, services-within-services, and usage shapes. The first move is always to break the bill into its actual line items. Most optimisation wins are concentrated in two or three line items, not spread evenly across everything.
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.
- 12d ago First seen · 247 lines · 291 tokens per session scan A 9fea07c97eca
infra-cost-assessment is a skill published in the GitHub repository EdytaKucharska/keel (4 stars, last pushed 2mo ago), licensed MIT. It adds 291 tokens to every session and 4,741 once invoked, about $0.0015 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
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
add-vercel
Add Vercel deployment capability to NanoClaw agents. Installs the Vercel CLI in agent containers and sets up OneCLI credential injection for api.vercel.com. Use when the user wants agents to deploy web applications to Vercel.
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
kubernetes-specialist
Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies…