What is exec-compile-specialist?

A build assistant for compiling TensorRT-LLM, an NVIDIA library for running large language models, from source. It works in a development container on a compute machine or submits the build as a SLURM cluster job.

Use it to build TensorRT-LLM directly on a compute node or through SLURM from a login node, including builds that use enroot containers.

It removes the need to handle the different build environments and cluster submission steps by hand.

How NVIDIA/TensorRT-LLM configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to NVIDIA/TensorRT-LLM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/NVIDIA/TensorRT-LLM/main/.claude/agents/exec-compile-specialist.md

Clone the repo

git clone --depth 1 https://github.com/NVIDIA/TensorRT-LLM

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/exec-compile-specialist/github.svg)](https://agentmods.dev/agents/nvidia/tensorrt-llm/exec-compile-specialist)

Your own site

<a href="https://agentmods.dev/agents/nvidia/tensorrt-llm/exec-compile-specialist"><img src="https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/exec-compile-specialist/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/nvidia/tensorrt-llm/exec-compile-specialist"><img src="https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/exec-compile-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00077	$0.01311
Opus 5.5	$0.00031	$0.00524
Sonnet 5.5	$0.00015	$0.00262
Haiku 4.5	$0.00008	$0.00131

Measured 7d ago against content hash f4545cc101f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

exec-compile-specialist 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 7d 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.

.claude/agents/exec-compile-specialist.md · 135 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

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.

7d ago Changed · +2 lines f4545cc101f7
2mo ago First seen · 133 lines · 77 tokens per session scan A 43b70078e2bb

Subscribe to this mod's changes

exec-compile-specialist is an agent published in the GitHub repository NVIDIA/TensorRT-LLM (15,021 stars, last pushed today), with no licence file. It adds 77 tokens to every session and 1,311 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.

Containers Data and AI DevOps and cloud PyTorch blackwell cuda llm-serving moe

exec-compile-specialist next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
exec-compile-specialistNVIDIA/TensorRT-LLM	Agent	15k	today	none	A	77	Claude Code
FAI Azure AKS Expertfrootai/frootai	Agent	7	4d ago	MIT	A	51	Claude Code
deploy-engineerrevfactory/harness-100	Agent	1.3k	7mo ago	Apache-2.0	A	27	Claude Code
pytorch-expertandisab/swe-marketplace	Agent	21	yesterday	MIT	A	17	Claude Code
pytorch-expertNickCrew/Claude-Cortex	Agent	66	4mo ago	MIT	A	23	Claude Code
ml-engineerEngineerWithAI/engineerwith-agents	Agent	4	9mo ago	MIT	A	55	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code

TensorRT-LLM: Agent for Claude Code