ad-model-onboard

A skill that converts a HuggingFace model into an AutoDeploy custom model used only for prefill, the stage that processes the input prompt before token generation.

In plain words
What is it for?
Onboarding HuggingFace models to AutoDeploy and running hierarchical equivalence tests against reference custom operations.
Why use it?
It provides a repeatable way to adapt a model while checking that its results match the reference model at several levels.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nvidia/tensorrt-llm/ad-model-onboard
Any agent
npx skills add NVIDIA/TensorRT-LLM --skill ad-model-onboard
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/TensorRT-LLM

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,825 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.07825
Opus 5 $0.00016 $0.03913
Sonnet 5 $0.00007 $0.01565
Haiku 4.5 $0.00003 $0.00783

Measured yesterday against content hash 55d86e643e86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ad-model-onboard 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 yesterday.

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.

.claude/skills/ad-model-onboard/SKILL.md · 359 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. yesterday First seen · 359 lines · 33 tokens per session scan A 55d86e643e86

Subscribe to this mod's changes

ad-model-onboard is a skill published in the GitHub repository NVIDIA/TensorRT-LLM (14,505 stars, last pushed 2d ago), with no licence file. It adds 33 tokens to every session and 7,825 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.

Related

Other skills, from other repositories

kl-consistency-test

Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…

sgl-project/sglang · 108 tokens

add-jit-kernel

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jitkernel module.

sgl-project/sglang · 27 tokens

sglang-runtime-context

How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points, resource/stream/buffer leases, per-forward flags), the CI guardrails that enforce the design, and the idioms for developing and testing…

sgl-project/sglang · 93 tokens

sglang-diffusion-add-model

Use when adding a new diffusion model or Diffusers pipeline to SGLang.

sgl-project/sglang · 24 tokens

sglang-diffusion-performance

Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.

sgl-project/sglang · 29 tokens

llm-torch-profiler-analysis

Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed. Use it to inspect an existing trace.json(.gz) or profile directory, or to drive live profiling against a running server when supported and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.

sgl-project/sglang · 84 tokens