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/guardrails/agents-mdgit clone --depth 1 https://github.com/NVIDIA-NeMo/GuardrailsWhat 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 | $0.02412 | $0.02412 |
| Opus 5 | $0.01206 | $0.01206 |
| Sonnet 5 | $0.00482 | $0.00482 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
Guardrails 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 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.
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.
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.
- yesterday First seen · 195 lines · 2,412 tokens per session scan A a331d7af11c9
Guardrails AGENTS.md is an instructions file published in the GitHub repository NVIDIA-NeMo/Guardrails (7,033 stars, last pushed 4d ago), with no licence file. It adds 2,412 tokens to every session, about $0.0121 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
Agent-Action-Guard AGENTS.md
AGENTS.md instructions for Pro-GenAI/Agent-Action-Guard, covering project: agent action guard, why it matters, quick usage (for agents), manual check and javascript runtime package.
Agent-Action-Guard CLAUDE.md
Claude Code instructions for Pro-GenAI/Agent-Action-Guard, a project described as: 🛡️ Safe AI Agents through Action Classifier.
crewAI AGENTS.md
Instructions for crewAIInc/crewAI, covering agent instructions for crewai oss, key guidelines, message content and changing docs.
fastmcp CLAUDE.md
Claude Code instructions for PrefectHQ/fastmcp, covering fastmcp development guidelines, required development workflow, repository structure, core mcp objects and development rules.
graphiti CLAUDE.md
Instructions for getzep/graphiti, covering claude.md, project overview, development commands, main development commands (run from project root) and install dependencies.
stagehand AGENTS.md
Instructions for browserbase/stagehand: Only a human may request changes to this file. Keep additions rare and limited to durable, repository-wide rules. -->.