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 rules/amdresearch/ai4science-studio/model-readmegit clone --depth 1 https://github.com/AMDResearch/ai4science-studioWhat 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 | $0.00000 | $0.00364 |
| Opus 5 | $0.00000 | $0.00182 |
| Sonnet 5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
model-readme 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.
What it actually says
Model README conventions
When creating or editing a README.md at <domain>/models/<slug>/README.md:
Required fields
Every model README must include these fields near the top, either as bold-label lines or a YAML-style table:
- Hugging Face model id — The canonical HF id (e.g.
nvidia/stormcast-v1-era5-hrrr) orN/Awith an "Obtaining model weights" section - License — SPDX identifier or link to the license
- Upstream code — Link to the GitHub repository
- Paper — Link to the paper (arXiv, journal, etc.) or "N/A"
- Task description — What the model does, in 1-2 sentences
Required sections
-
Recipes table — List all available recipes with links:
## Recipes | Recipe | Summary | |--------|---------| | [`recipes/inference/`](recipes/inference/) | ... | -
AMD / ROCm notes — Only what has actually been validated. Include container image, hardware tested, and any ROCm-specific findings.
-
On-disk folder name — If the folder name differs from the HF slug, document the mapping.
Companion files
Every model folder should also have:
model.yaml— Machine-readable manifest with the same metadatarecipes/— At least one recipe subfolderexamples/— Ready-to-run scripts withREADME.md
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 · 41 lines · 0 tokens per session scan A 760ac974de99
model-readme is a cursor rule published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 364 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.