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 skills add Ascend/agent-skills --skill drivingsdk-ascend-model-migrationgit clone --depth 1 https://github.com/Ascend/agent-skillsWrote 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/skills/ascend/agent-skills/drivingsdk-ascend-model-migration)<a href="https://agentmods.dev/skills/ascend/agent-skills/drivingsdk-ascend-model-migration"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/drivingsdk-ascend-model-migration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ascend/agent-skills/drivingsdk-ascend-model-migration"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/drivingsdk-ascend-model-migration.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00039 | $0.01420 |
| Opus 5 | $0.00019 | $0.00710 |
| Sonnet 5 | $0.00008 | $0.00284 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
ascend-model-migration 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 11d 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.
The source is not reproduced here
Licensed MulanPSL-2.0
The repository is licensed MulanPSL-2.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
29 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.
- ascend-mmlab-install-suite/detectron2/SKILL.md 1.7 KB
- ascend-mmlab-install-suite/mmcv/SKILL.md 2.7 KB
- ascend-mmlab-install-suite/mmdet/SKILL.md 1.9 KB
- ascend-mmlab-install-suite/mmdet3d/SKILL.md 2.4 KB
- ascend-mmlab-install-suite/README.md 2.4 KB
- ascend-mmlab-install-suite/script/verify_mmlab_imports.py 1.8 KB runs code
- ascend-mmlab-install-suite/SKILL.md 3.4 KB
- model-migration/SKILL.md 4.8 KB
- model-training/SKILL.md 4.5 KB
- README.md 8.5 KB
- ssh-connection/_lib/_python.sh 697 B runs code
- ssh-connection/_lib/ssh-config.py 3.4 KB runs code
- ssh-connection/config.example.yaml 2.1 KB
- ssh-connection/config.yaml 745 B
- ssh-connection/connect/scripts/ssh-download.sh 3.1 KB runs code
- ssh-connection/connect/scripts/ssh-exec.sh 1.5 KB runs code
- ssh-connection/connect/scripts/ssh-job.sh 5.8 KB runs code
- ssh-connection/connect/scripts/ssh-test.sh 1.4 KB runs code
- ssh-connection/connect/scripts/ssh-upload.sh 3.1 KB runs code
- ssh-connection/connect/SKILL.md 1.8 KB
- ssh-connection/debug/SKILL.md 2.8 KB
- ssh-connection/deploy/scripts/ssh-deploy.sh 2.5 KB runs code
- ssh-connection/deploy/SKILL.md 977 B
- ssh-connection/long-task/scripts/checkpoint.sh 1.9 KB runs code
- ssh-connection/long-task/SKILL.md 2.9 KB
- ssh-connection/README.md 2.1 KB
- ssh-connection/SKILL.md 1.3 KB
- ssh-connection/tunnel/scripts/ssh-tunnel.sh 9.8 KB runs code
- ssh-connection/tunnel/SKILL.md 1.1 KB
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.
- 11d ago First seen · 170 lines · 39 tokens per session scan A e5f603fa7da7
ascend-model-migration is a skill published in the GitHub repository Ascend/agent-skills (40 stars, last pushed 4mo ago), licensed MulanPSL-2.0. It adds 39 tokens to every session and 1,420 once invoked, about $0.0002 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 skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
minicpm5-deploy-vllm-ascend
Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.