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 nimadorostkar/Claude-Skills-collection --skill model-selectiongit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/model-selection)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/model-selection"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/model-selection/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/nimadorostkar/claude-skills-collection/model-selection"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/model-selection.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 | $0.00041 | $0.01235 |
| Opus 5 | $0.00020 | $0.00617 |
| Sonnet 5 | $0.00008 | $0.00247 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
model-selection 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Selection
Purpose
Choose the model that meets the task's requirements at the lowest cost and latency. Most production LLM features run on a model several times more expensive than the task requires, because nobody measured the cheaper one.
When to Use
- Choosing a model for a new feature.
- Reducing the cost or latency of an existing feature.
- Evaluating whether a newly released model is worth migrating to.
- Designing a routing strategy across several models.
Capabilities
- Task-to-capability matching.
- Cost and latency modeling at real volume.
- Routing: cheap model first, escalate on difficulty.
- Benchmark interpretation and its limits.
- Migration and re-evaluation.
Inputs
- The task, and the accuracy it genuinely requires.
- Volume, latency budget, and cost budget.
- An evaluation set — without one, this is guesswork.
Outputs
- A model choice justified by measurement on your data.
- A cost and latency projection at real volume.
- A routing strategy, where one is warranted.
Workflow
- Start with the cheapest plausible model — Not the best one. Measure it on your evaluation set. Escalate only if it fails, and only as far as necessary.
- Measure on your data, not on benchmarks — A model that leads on MMLU may be worse at your specific extraction task. Public benchmarks measure general capability, and your task is not general.
- Model the cost at real volume — A per-call cost difference that looks trivial becomes the dominant line item at a million calls a month. Do the arithmetic before choosing.
- Consider routing — Send everything to a small model; escalate the cases it flags as low-confidence to a larger one. This frequently captures most of the accuracy at a fraction of the cost.
- Re-evaluate on model updates — Provider models change under the same name. A prompt tuned six months ago on a model that has since been updated may no longer be optimal.
Best Practices
- The most common mistake is defaulting to the most capable model for everything. Classification, extraction, and routing tasks are usually solved by a small model at a tenth of the cost and a fifth of the latency.
- Public benchmarks are contaminated and gamed. They are a rough capability ordering, not a prediction of performance on your task.
- Latency matters more than cost for user-facing features, and cost matters more than latency for batch processing. Optimize for the one that binds.
- A cheaper model with better prompting often beats a more expensive model with worse prompting. Improve the prompt before upgrading the model.
- Test the failure mode, not just the accuracy. A small model that fails loudly is safer than a large one that fails plausibly.
- Do not hard-code the model name across the codebase. Configure it, so migration is a config change rather than a search-and-replace.
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.
- 11d ago First seen · 116 lines · 41 tokens per session scan A 13fdbc06c895
model-selection is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 23d ago), licensed MIT. It adds 41 tokens to every session and 1,235 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
datarobot-agent-assist
Use when the user wants to design, build, code, simulate, or deploy an AI agent (not a predictive model) to DataRobot; mentions agentspec.md, dr-assist, datarobot-agent-assist, dress rehearsal, swarm simulation, or the DataRobot agent template; wants to scaffold a LangGraph, CrewAI, LlamaIndex, NAT, or Base agent…
datarobot-agent-assist-build
Use when the user wants to design, build, code, or deploy an AI agent on DataRobot; mentions agentspec.md, dress rehearsal, the DataRobot agent template, LangGraph, CrewAI, LlamaIndex, NAT, Base agents, MCP servers, backend APIs, custom frontends, or the DataRobot CLI.
datarobot-predictions
Tools and guidance for making predictions with DataRobot deployments, including real-time predictions, batch scoring, prediction dataset generation, and prediction explanations (SHAP/XEMP). Use when making predictions, running batch scoring, generating prediction datasets, or explaining individual predictions from a…
datarobot-model-explainability
Tools and guidance for model explainability, prediction explanations, feature impact analysis, SHAP values, SHAP distributions, anomaly assessment, and model diagnostics. Use when analyzing model explanations, feature impact, SHAP values, SHAP distributions, anomaly assessment, or diagnosing model behavior.
datarobot-model-training
Comprehensive guidance for training models in DataRobot, including project creation, AutoML configuration, feature engineering, and model selection. Use when training models, creating AutoML projects, or selecting models in DataRobot.
datarobot-model-deployment
Tools and guidance for deploying DataRobot models, managing deployments, configuring prediction environments, and deployment operations. Use when deploying models, creating or updating deployments, or configuring prediction environments.