Coreweave Cost Tuning

What it does

When your agent uses it

• Reducing GPU spend
• Selecting cost-effective instances
• Implementing scale-to-zero for dev workloads
• With phrases like coreweave cost

Example prompts

• “coreweave cost”
• “coreweave pricing”
• “reduce coreweave spend”
• “/coreweave-cost-tuning”

Requirements

• Python 3
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(kubectl:*), Grep

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Baseline seven days of GPU utilization, queue time, request latency, error rate,
2. 2Propose one reversible change—right-size a non-production workload, set a
3. 3Compare the canary against its SLO and budget for an agreed observation window.
4. 4Record the instance choice, owner, forecast, and rollback trigger in the

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(kubectl:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • kubectl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • coreweave.com
  • docs.coreweave.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Coreweave Cost Tuning loads about 1.3k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 446 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~79

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 446 words, ~1,251 tokens.

name

coreweave-cost-tuning

description

Optimize CoreWeave GPU cloud costs with right-sizing and scheduling. Use when reducing GPU spend, selecting cost-effective instances, or implementing scale-to-zero for dev workloads. Trigger with phrases like "coreweave cost", "coreweave pricing", "reduce coreweave spend", "coreweave budget".

allowed-tools

Read, Write, Edit, Bash(kubectl:*), Grep

compatibility

Designed for Claude Code

version

1.11.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, gpu-cloud, kubernetes, inference, coreweave

autoscaling.knative.dev/minScale: "0"
autoscaling.knative.dev/scaleDownDelay: "5m"

def recommend_gpu(model_size_b: float, inference_only: bool = True) -> str:
    if model_size_b <= 7:
        return "L40" if inference_only else "A100_PCIE_80GB"
    elif model_size_b <= 13:
        return "A100_PCIE_80GB"
    elif model_size_b <= 70:
        return "A100_PCIE_80GB (4x tensor parallel)"
    else:
        return "H100_SXM5 (8x tensor parallel)"

# 70B model at 4-bit fits on single A100-80GB instead of 4x
vllm serve meta-llama/Llama-3.1-70B-Instruct-AWQ --quantization awq

kubectl -n inference-staging patch deployment summarizer \
  --type merge -p '{"spec":{"template":{"spec":{"containers":[{"name":"server","resources":{"limits":{"nvidia.com/gpu":1}}}]}}}}'
kubectl -n inference-staging rollout status deployment/summarizer --timeout=10m

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/coreweave-cost-tuning of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287