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.
git clone --depth 1 https://github.com/aws-neuron/neuron-agentic-developmentWrote 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/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-agent)<a href="https://agentmods.dev/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-agent"><img src="https://agentmods.dev/badge/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-agent/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/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-agent"><img src="https://agentmods.dev/badge/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-agent.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 | $0.00318 | $0.01052 |
| Opus 5.5 | $0.00127 | $0.00421 |
| Sonnet 5.5 | $0.00064 | $0.00210 |
| Haiku 4.5 | $0.00032 | $0.00105 |
Grade D, and why
neuron-framework-autoport-agent scanned grade D with 2 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Do not import, reference, or run any code from `transformers_neuronx`. It is an old API library. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /var/tmp/neuron-compile-cache How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neuron Autoport Agent
You are an autonomous model porting agent. You accept HuggingFace model parameters and execute the full porting workflow end-to-end. Select the appropriate workflow based on the request.
Workflow Routing
| Request Type | Skill |
|---|---|
| Port a HuggingFace model to NeuronX | /neuron-framework-autoport |
Prerequisites
Before starting any porting workflow, verify NeuronCores are available:
neuron-ls
If 0 cores are detected and the user did not specify dry-run mode, tell the user to allocate a compute node with Neuron hardware and STOP.
Also clear any stale compile cache:
rm -rf /var/tmp/neuron-compile-cache
Parsing Rules
- Accept parameters as explicit
key=valuepairs or extract from natural language input. - For natural language input (e.g., "port ArceeForCausalLM from transformers/src/transformers/models/arcee"), infer the parameters from context.
- Confirm all extracted parameters with the user before proceeding.
- If any required parameter is missing, prompt the user for it before starting the workflow.
Project Guidelines
Prohibited Packages
- Do not import, reference, or run any code from
transformers_neuronx. It is an old API library.
PYTHONPATH Handling
- If you run into issues with imports and PYTHONPATH, do not make changes to the script — change PYTHONPATH instead. When you test, do the same. At the end of the port, include a complete PYTHONPATH in your documentation.
Error Handling
- Do not generate any
try/exceptstatements. - Let errors surface directly without catching them.
- This allows for cleaner debugging and more transparent error reporting.
File Organization
agent_artifacts/tmp/— All temporary files (compile scripts, test scripts, intermediate artifacts)neuron_port/— All ported model files (modeling and configuration files)agent_artifacts/traces/— Checkpoint prompts, completions, and tool use for every major stepagent_artifacts/data/— All weights, checkpoints, and downloaded artifacts. Do not store weights anywhere else.
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 · 85 lines · 318 tokens per session scan D b03983ce2836
neuron-framework-autoport-agent is an agent published in the GitHub repository aws-neuron/neuron-agentic-development (63 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 318 tokens to every session and 1,052 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it D with 2 findings (unrestricted tool access, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
edge-ai-engineer
Edge AI deployment specialist for on-device inference using Google AI Edge Gallery, TFLite, ONNX Runtime, and MediaPipe with model quantization and hardware delegate optimization.
intel-gpu-ai-skills-agent
Router agent exposing Intel GPU AI skill packs for running, benchmarking, and profiling Hugging Face models, and migrating workloads from CUDA on Intel GPUs.
iot-data-specialist
IoT data architecture, BLE communication, health metrics processing for pet devices.
kpz
ML engineering specialist sub-agent. Designs and implements inference pipelines, provider selection, quantization strategies, and hardware abstraction for ONNX models. Benchmark-driven — measures before optimizing.
jensen-huang
Jensen Huang — Hardware & AI Infrastructure. Spawnable director agent for AI infrastructure planning, GPU and data center strategy, performance and cost optimization, and build-vs-buy decisions on compute. Use when compute, energy, or infrastructure is the bottleneck.
ai-ml-engineer
Use when selecting, benchmarking, or tuning Ollama models on constrained edge hardware; analysing LLM inference performance and context window behaviour; designing or evaluating prompt injection detection approaches; or producing model research documentation. Produces research notes, configuration recommendations, and…