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 agentmods add instructions/nvidia-nemo/datadesigner/agents-mdgit clone --depth 1 https://github.com/NVIDIA-NeMo/DataDesignerWhat 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 | $0.00906 | $0.00906 |
| Opus 5 | $0.00453 | $0.00453 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
DataDesigner 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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is for agents developing DataDesigner — the codebase you are working in.
If you are an agent helping a user build a dataset, use the data-designer skill and the product documentation instead.
DataDesigner is an NVIDIA NeMo framework for creating synthetic datasets from scratch. Users declare what their data should look like (columns, types, relationships, validation rules); the engine figures out how to generate it. Every change you make should preserve this "declare, don't orchestrate" contract.
The Layering Is Structural
The data_designer namespace is split across three installable packages that merge at runtime via PEP 420 implicit namespace packages (no top-level __init__.py).
| Package | Path | Owns |
|---|---|---|
data-designer-config |
packages/data-designer-config/ |
data_designer.config — column configs, model configs, sampler params, builder API, plugin system, lazy imports |
data-designer-engine |
packages/data-designer-engine/ |
data_designer.engine — column generators, dataset builders, DAG execution, model facade, validators, sampling |
data-designer |
packages/data-designer/ |
data_designer.interface — public DataDesigner class, results, errors; data_designer.cli — CLI entry point; data_designer.integrations |
Dependency direction (left depends on right): interface → engine → config. Never import against this flow.
Core Concepts
- Column — a named field in the output dataset, defined by a column config
- Sampler — a built-in statistical generator (UUID, Category, Uniform, Gaussian, Person, DateTime, etc.)
- Seed dataset — an existing dataset used as input for generation
- Processor — a post-generation transformation applied to column values
- Model — an LLM endpoint configured via
ModelConfigand accessed through the model facade - Plugin — a user-supplied extension registered via entry points (custom column generators, validators, profilers)
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.
- 3d ago First seen · 57 lines · 906 tokens per session scan A b423835c10e7
DataDesigner AGENTS.md is an instructions file published in the GitHub repository NVIDIA-NeMo/DataDesigner (2,194 stars, last pushed 4d ago), licensed Apache-2.0. It adds 906 tokens to every session, about $0.0045 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.
Other instructions, from other repositories
Omni-Rewriter AGENTS.md
Instructions for WayneJin0918/Omni-Rewriter: Maintainer and coding-agent conventions live in docs/AGENTS.md. Also see .cursor/skills/omni-rewriter-h3-pe/SKILL.md, .cursor/skills/omni-rewriter-model-contribution/SKILL.md, and .cursor/skills/omni-rewriter-promo-pipeline/SKILL.md.
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
nimbalyst AGENTS.md
AGENTS.md instructions for nimbalyst/nimbalyst: At the beginning of every AI session, read the root CLAUDE.md and any applicable package-level CLAUDE.md before taking actions.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).