audit-models

audit-models is a command for Claude Code from AMDResearch/ai4science-studio. It costs 0 tokens per session (276 once invoked), scanned A, original, MIT.

A readiness audit for the scientific models listed in a project's models.yaml file. It checks whether each model has its documentation, metadata, runnable examples, cluster script, and at least one recipe.

In plain words
What is it for?
Use it to produce a per-model checklist and identify missing README files, manifests, Docker or preflight scripts, run scripts, SLURM scripts, examples documentation, or recipes.
Why use it?
It shows which models are ready to use and which have missing setup pieces. This makes gaps visible without inspecting every model folder manually.

Command for Claude Code

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 commands/amdresearch/ai4science-studio/audit-models
Clone the repo
git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

Made for: Claude Code.

Wrote 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.

agentmods badge for audit-models

README.md
[![agentmods](https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/audit-models.svg)](https://agentmods.dev/commands/amdresearch/ai4science-studio/audit-models)
Your own site
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/audit-models"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/audit-models.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 276 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00276
Opus 5 $0.00000 $0.00138
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00028

Measured 3d ago against content hash c79f4243253b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-models 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.

.claude/commands/audit-models.md · 32 lines

What it actually says

Check model readiness status

Audit which models are fully set up and which have gaps.

How to respond

For each model listed in models.yaml, check the following files exist:

Check File pattern
Model README <path>/README.md
Model manifest <path>/model.yaml
Docker script <path>/examples/docker_run.sh
Preflight script <path>/examples/preflight_*.py
Run script <path>/examples/run_*.{sh,py}
SLURM script <path>/examples/sbatch_*_amd.sh
Examples README <path>/examples/README.md
At least one recipe <path>/recipes/*/README.md

Present the results as a checklist table:

Model README model.yaml docker preflight run script SLURM examples README recipes
StormCast Y Y Y Y Y Y Y 2
... ... ... ... ... ... ... ... ...

Flag any models with missing items and suggest what to add.

Arguments

$ARGUMENTS

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.

  1. 3d ago First seen · 32 lines · 0 tokens per session scan A c79f4243253b

Subscribe to this mod's changes

audit-models is a command 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 276 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.