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/cosmos-curator/claude-mdgit clone --depth 1 https://github.com/NVIDIA/cosmos-curatorWrote 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.
[](https://agentmods.dev/instructions/nvidia/cosmos-curator/claude-md)<a href="https://agentmods.dev/instructions/nvidia/cosmos-curator/claude-md"><img src="https://agentmods.dev/badge/instructions/nvidia/cosmos-curator/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.00029 |
| Opus 5 | $0.00015 | $0.00015 |
| Sonnet 5 | $0.00006 | $0.00006 |
| Haiku 4.5 | $0.00003 | $0.00003 |
Grade A, and why
cosmos-curator CLAUDE.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.
What it actually says
Agent Instruction Loader
@./AGENTS.md
AGENTS.md is the canonical instruction file. Edit it rather than this loader.
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 Changed · -81 lines · -1,264 tokens per session 89df9f45dd34
- 5d ago First seen · 87 lines · 1,293 tokens per session scan A 1012830df6bd
cosmos-curator CLAUDE.md is an instructions file published in the GitHub repository NVIDIA/cosmos-curator (264 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session, about $0.0001 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
Score-CAM CLAUDE.md
Instructions for tabayashi0117/Score-CAM, covering claude.md, what this repository is, layout, non-negotiable rules and paper fidelity.
cdc-health-mcp-server CLAUDE.md
Instructions for cyanheads/cdc-health-mcp-server, covering agent protocol, domain, api surface, socrata api endpoints and cdc wonder api.
AutoTrainess AGENTS.md
Instructions for simple-agent-lab/AutoTrainess, covering agents.md, objective, hard constraints, experiment guidance and stage rules.
nvalchemi-toolkit CLAUDE.md
Claude Code instructions for NVIDIA/nvalchemi-toolkit, a project described as: ALCHEMI Toolkit is a developer toolkit for accelerating training and inference for AI in chemistry and material science.
medgemma-mcp CLAUDE.md
Claude Code instructions for Tom-R-Main/medgemma-mcp, covering medgemma mcp server, project overview, architecture, key technical decisions and development rules.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.