awslabs/agent-plugins is a collection of plugins, skills, instructions, an MCP server, a hook, and a setting that guide AI coding agents in architecting, deploying, and operating software on Amazon Web Services. It is for developers using coding agents such as Claude Code, Codex, and Cursor with AWS projects. The catalogue entries are the repository's own agent workflows and supporting components.
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 awslabs/agent-plugins --skill model-selectiongit clone --depth 1 https://github.com/awslabs/agent-pluginsWrote 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/awslabs/agent-plugins/model-selection)<a href="https://agentmods.dev/skills/awslabs/agent-plugins/model-selection"><img src="https://agentmods.dev/badge/skills/awslabs/agent-plugins/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/awslabs/agent-plugins/model-selection"><img src="https://agentmods.dev/badge/skills/awslabs/agent-plugins/model-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 41 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00098 | $0.00791 |
| Opus 5.5 | $0.00039 | $0.00316 |
| Sonnet 5.5 | $0.00020 | $0.00158 |
| Haiku 4.5 | $0.00010 | $0.00079 |
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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Selection
Guides the user through selecting a base model based on their use case.
When to Use
- User asks which model to use
- User wants to select or change their base model
- User mentions a model name or family (e.g., "Llama", "Mistral", "Nova") — the exact Hub model ID still needs to be resolved
- User wants to evaluate a base model before deciding whether to finetune
Prerequisites
- A
use_case_spec.mdfile exists. If not, activate the use-case-specification skill to generate it first.
Workflow
Step 1: Check Region
Run:
python -c "import boto3; print(boto3.session.Session().region_name)"
None→ STOP. Tell user: "Set your region viaexport AWS_DEFAULT_REGION=us-west-2oraws configure."- Set → store REGION in context, continue.
Step 2: Discover Hub
-
List all available SageMaker Hubs in the user's region by calling the SageMaker
ListHubsAPI using theaws___call_awstool. -
From the results, filter out any hub whose
HubDescriptioncontains "AI Registry" — these do not contain JumpStart models. -
The remaining hubs are eligible (e.g.,
SageMakerPublicHuband any private hubs). -
If exactly one eligible hub exists, use it automatically — do not ask the user.
-
If multiple eligible hubs exist, present them to the user and ask which one to use. Example:
I found the following model hubs: - SageMakerPublicHub — SageMaker Public Hub - Private-Hub-XYZ — Private Hub models Which hub would you like to use? -
Store the selected hub name for use in subsequent steps.
Step 3: Select Base Model
First, retrieve all available SageMaker Hub model names by running: python model-selection/scripts/get_model_names.py <hub-name>.
Present all available models to the user with their licenses before making any recommendations. Cross-reference the model list with references/model-licenses.md and display each as <model name> - [<license>](<url>). For example: "Qwen3-4B - Apache 2.0"
What ships with it
11 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.
- references/benchmarks/agenticIndex.md 2.8 KB
- references/benchmarks/codingIndex.md 2.8 KB
- references/benchmarks/gpqa.md 2.8 KB
- references/benchmarks/hle.md 2.8 KB
- references/benchmarks/ifbench.md 2.7 KB
- references/benchmarks/intelligenceIndex.md 2.7 KB
- references/benchmarks/mmmuPro.md 3.0 KB
- references/benchmarks/tau2.md 2.8 KB
- references/model-licenses.md 7.8 KB
- references/model-selection.md 8.0 KB
- scripts/get_model_names.py 1.0 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.
- 1mo ago First seen · 77 lines · 98 tokens per session scan A 04b6f9772633
model-selection is a skill published in the GitHub repository awslabs/agent-plugins (924 stars, last pushed 3d ago), licensed Apache-2.0. It adds 98 tokens to every session and 791 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
aiml-gpu-training-cluster-investigation
Use this skill for GPU training or inference clusters on SageMaker HyperPod (Slurm or EKS), ParallelCluster, or self-managed EC2/EKS GPU instances. It adds three things. First, a GPU evidence coverage audit that proves per node whether kernel Xid logs and HyperPod health-agent detections were actually arriving, hour…
sagemaker-ai-ops-review
Amazon SageMaker AI Operational Review. Use this skill when a user asks to review, audit, or assess Amazon SageMaker AI workloads (endpoints, training jobs, pipelines, notebooks, Studio domains) for best-practices posture across Security, Performance, Cost Optimization, Service Quotas, Resiliency, Operational…
agentproto-llm-endpoint
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
llm-evaluation
LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.
rag-implementation
Comprehensive guide to implementing RAG systems including vector database selection, chunking strategies, embedding models, and retrieval optimization. Use when building RAG systems, implementing semantic search, optimizing retrieval quality, or debugging RAG performance issues.
huggingface-transformers
Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP tasks, or optimizing transformer inference.