A set of tools for downloading ModelScope model weights, continuing interrupted downloads, checking their status, and verifying their SHA256 checksums. ModelScope is a platform that hosts machine-learning models.

Use it to download, resume, monitor, repair, or verify ModelScope models in local directories.

It gives downloads an explicit local destination and supports resume and integrity checks, so incomplete or corrupted model files can be identified.

How maoxx241/vllm-ascend-workspace configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to maoxx241/vllm-ascend-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/maoxx241/vllm-ascend-workspace/main/.agents/skills/modelscope/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspace

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/modelscope.svg)](https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/modelscope)

Your own site

<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/modelscope"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/modelscope.svg" alt="Measured on agentmods" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 781 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high System Prompt Leakage · line 79
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.00781
Opus 5	$0.00034	$0.00391
Sonnet 5	$0.00013	$0.00156
Haiku 4.5	$0.00007	$0.00078

Measured 8d ago against content hash b4b5377a496d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

modelscope 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 8d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/download_from_modelscope.py, scripts/modelscope_auto.py, scripts/modelscope_download_status.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/modelscope/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ModelScope

Use the bundled scripts from this skill directory. Prefer the compact manager first:

scripts/modelscope_auto.py - status, auto-resume, background download, and post-download verification
scripts/download_from_modelscope.py - low-level single-model downloader
scripts/modelscope_download_status.py - low-level size status
scripts/verify_modelscope_sha256.py - low-level SHA256 verification

Do not inline long nohup/setsid shell blocks. Do not read or tail large logs unless a task fails or the user asks.

Model Mapping

Represent every model as MODEL_ID=LOCAL_DIR.

MODEL_ID must be namespace/name.
LOCAL_DIR must be explicit.
If the user says “to /root” without a model subdirectory, use /root/namespace/name.
Use revision master unless specified.
Repeat --model MODEL_ID=LOCAL_DIR for multiple models.

Download / Resume / Auto Complete

For $modelscope download, resume, repair-after-approval, or “check and continue if incomplete”, run:

python3 "$SKILL_DIR/scripts/modelscope_auto.py" ensure \
  --model "$MODEL_ID=$LOCAL_DIR" \
  --revision "$REVISION"

ensure behavior:

If a task is active, leave it running and report compact status.
If official files are incomplete and no task is active, start a detached background worker in the same LOCAL_DIR.
If files are complete but verification is missing or stale, start detached SHA256 verification.
If verification reports real missing, size mismatch, or SHA256 mismatch, report it and ask before repair.
It preserves partial files and never deletes weights.

The manager writes download.pid, download.launch.log, download.log, verify.log, modelscope_sha256.report.json, modelscope_sha256.tsv, and SHA256SUMS in LOCAL_DIR.

Proxy options:

Pass no proxy option by default.
Add --no-proxy only when requested.
Add --proxy "$PROXY_URL" only when provided.

Status

For explicit status only:

python3 "$SKILL_DIR/scripts/modelscope_auto.py" status \
  --model "$MODEL_ID=$LOCAL_DIR" \
  --revision "$REVISION"

Read the full file on GitHub · 85 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 85 lines · 67 tokens per session scan A b4b5377a496d

Subscribe to this mod's changes

modelscope is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 781 once invoked, about $0.0003 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.

Data and AI

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

vllm-ascend-workspace: Skill for Codex