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 finetuninggit 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/finetuning)<a href="https://agentmods.dev/skills/awslabs/agent-plugins/finetuning"><img src="https://agentmods.dev/badge/skills/awslabs/agent-plugins/finetuning/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/finetuning"><img src="https://agentmods.dev/badge/skills/awslabs/agent-plugins/finetuning.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 | $0.00085 | $0.02269 |
| Opus 5.5 | $0.00034 | $0.00908 |
| Sonnet 5.5 | $0.00017 | $0.00454 |
| Haiku 4.5 | $0.00009 | $0.00227 |
Grade A, and why
finetuning 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prerequisites
Before starting this workflow, verify:
-
A
use_case_spec.mdfile exists- If missing: Activate the
use-case-specificationskill first, then resume - DON'T EVER offer to create a use case spec without activating the use-case-specification skill.
- If missing: Activate the
-
A fine-tuning technique (SFT, DPO, RLVR, RLAIF, or CPT/RFT (for Nova)) and base model have already been selected
- If missing: Activate the
model-selectionand/orfinetuning-techniqueskills to collect what's missing, then resume - Don't make recommendations on the spot. You MUST activate the appropriate skill.
- If missing: Activate the
-
A base model name available on SageMakerHub has been identified
- If missing: Activate the
model-selectionskill to get it - Important: Only use the model name that
model-selectionretrieves, as it may differ from other commonly used names for the same model
- If missing: Activate the
-
The SDK environment has been verified (SDK version, region, execution role)
- If not done: Activate the
sdk-getting-startedskill first, then resume
- If not done: Activate the
-
A training dataset uploaded to a bucket in the environment's default region.
- If not met: Help the user upload the dataset to the correct S3
Critical Rules
Code Generation Rules
- ✅ Use EXACTLY the imports shown in each code template
- ❌ Do NOT add additional imports even if they seem helpful
- ❌ Do NOT create variables before they're needed in that section
- 📋 Copy the code structure precisely - no improvisation
- 🎯 Follow the minimal code principle strictly
- ✅ When writing code, make sure the indentation and f strings are correct
User Communication Rules
- ❌ NEVER offer to move on to a downstream skill while training is in progress (logically impossible)
- ❌ NEVER set ACCEPT_EULA to True without explicit user confirmation in the conversation
- ✅ Always mention both the number AND title of sections you reference
- ✅ If user asks how to run (notebook): If
run_cellis available, offer to run it. Otherwise, tell them to run cells one by one (mention ipykernel requirement). - ✅ If user asks how to run (script): Tell them to run with
python3 <script>.py
What ships with it
13 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.
- code_templates/dpo.py 5.7 KB runs code
- code_templates/rlaif_builtin.py 5.5 KB runs code
- code_templates/rlaif_custom_prompt.py 6.0 KB runs code
- code_templates/rlvr.py 6.2 KB runs code
- code_templates/sft.py 5.5 KB runs code
- references/code_output_guide.md 3.2 KB
- references/continuous_customization.md 8.5 KB
- references/eula_links.md 7.8 KB
- references/rlaif_guide.md 3.8 KB
- references/rlvr_reward_function.md 10 KB
- scripts/mlflow_reference.py 840 B runs code
- templates/nova_rlvr_reward_function_source_template.py 13 KB runs code
- templates/rlvr_reward_function_source_template.py 9.2 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 · 183 lines · 85 tokens per session scan A 02cacd845c06
finetuning is a skill published in the GitHub repository awslabs/agent-plugins (924 stars, last pushed 6d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,269 once invoked, about $0.0003 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.