What is nvcf AGENTS.md?

A coding-agent guide for NVCF, NVIDIA Cloud Functions, a system for running cloud-based functions. It explains the repository layout, shared code from other repositories, ownership files, tools, documentation, and local testing rules.

Use it when modifying NVCF services, infrastructure, migrations, tools, tests, documentation, or imported repository snapshots.

It helps an agent navigate a large repository and avoid mistakes with pinned external code, subtree ownership, Python commands, and test environments.

nvcf AGENTS.md — Instructions file by NVIDIA

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 instructions/nvidia/nvcf/agents-md

Clone the repo

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

Made for: Codex, OpenCode.

Per session 5,219 This file is loaded in full into every session.

When invoked 5,219 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original 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	$0.05219	$0.05219
Opus 5	$0.02610	$0.02610
Sonnet 5	$0.01044	$0.01044
Haiku 4.5	$0.00522	$0.00522

Measured 2d ago against content hash e99f650637ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nvcf AGENTS.md 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 2d 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.

AGENTS.md · 476 lines

How it starts

The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Guide for AI Coding Agents

Quick reference for NVCF (NVIDIA Cloud Functions) in this repository.

Repo Layout

This repo is an umbrella layout: upstream services appear as ordinary directories arranged under src/, deploy/, infra/, and migrations/ according to imports.yaml. Goal: over time, land and maintain code here natively while upstream-owned sources are still tracked by commit pin. Tooling lives under tools/ and tests/.

Use python3, not python, when Python is needed. Use the nearest nested AGENTS.md for subtree-specific guidance.

Useful pointers:

BAZEL.md for the contributor-facing Bazel build path
docs/AGENTS.md for in-repo user and developer documentation
tools/AGENTS.md for repo tooling
imports.yaml for subtree ownership and commit pins
.cursor/skills/documentation-style/SKILL.md for docs style
.cursor/skills/ for root dev-skill symlink fanout
ai-tooling/user/skills/ and ai-tooling/dev/skills/ for public skills

If a referenced skill is outdated, update it before finishing.

Cross-repo and stack routing

Documentation is monorepo-native. User docs, version catalogs, and Fern navigation are owned under docs/ and fern/ in this repository. Do not route documentation changes through an external documentation repository or an external workspace index. Start with docs/AGENTS.md and the nearest nested guidance.

Use imports.yaml to decide whether a subtree is monorepo-native or still owned by an upstream repo. Native subprojects are edited here. Upstream-owned subtrees usually need the change in the upstream repo and a later commit-pin update.

For self-managed stack ownership, deployment order, chart/image-source mapping, or "which subtree owns this" questions, use:

.cursor/skills/nvcf-explore-stack/SKILL.md for the in-repo Helmfile, dependency, chart, hook, and image-source map

Do not copy workspace routing boilerplate into subtree AGENTS.md files. Local guidance should only record subtree-specific ownership exceptions, adjacent subtrees that commonly need follow-up, and commands that must be run from that subtree.

Read the full file on GitHub · 476 lines

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.

2d ago First seen · 476 lines · 5,219 tokens per session scan A e99f650637ed

Subscribe to this mod's changes

nvcf AGENTS.md is an instructions file published in the GitHub repository NVIDIA/nvcf (202 stars, last pushed 2d ago), licensed Apache-2.0. It adds 5,219 tokens to every session, about $0.0261 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.

DevOps and cloud GPU NVIDIA Testing Writing and docs cloud-functions inference kubernetes serverless-gpu

nvcf AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md - Guide for AI Coding Agents

Repo Layout

Cross-repo and stack routing

What this file has done since we first saw it

Other instructions, from other repositories

DeepSpeed AGENTS.md

homelab-monitor CLAUDE.md

DeepSpeed CLAUDE.md

kubeledger CLAUDE.md

timoni AGENTS.md

netdata AGENTS.md