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-ai-coding/awesome-ascend-skills --skill deepfrigit clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-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-ai-coding/awesome-ascend-skills/deepfri)<a href="https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/deepfri"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/deepfri/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-ai-coding/awesome-ascend-skills/deepfri"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/deepfri.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 | $0.00089 | $0.03963 |
| Opus 5 | $0.00044 | $0.01982 |
| Sonnet 5 | $0.00018 | $0.00793 |
| Haiku 4.5 | $0.00009 | $0.00396 |
Grade A, and why
ai-for-science-deepfri scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
wget https://users.flatironinstitute.org/~renfrew/DeepFRI_data/trained_models.tar.gz The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
7 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.
- references/weight-conversion-checklist.md 845 B
- scripts/convert_weights.py 5.8 KB runs code
- scripts/predict_npu.py 2.2 KB runs code
- scripts/torch_layers.py 6.8 KB runs code
- scripts/torch_model.py 3.9 KB runs code
- scripts/torch_predictor.py 7.7 KB runs code
- scripts/verify_accuracy.py 3.0 KB runs code
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.
- 7d ago First seen · 342 lines · 89 tokens per session scan A f2a8c25a2ad2
ai-for-science-deepfri is a skill published in the GitHub repository ascend-ai-coding/awesome-ascend-skills (168 stars, last pushed yesterday), with no licence file. It adds 89 tokens to every session and 3,963 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
fine-tuning-serving-openpi
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging…
tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.
autoprotocol-experiment-plan-starter
Use this skill to generate a deterministic Autoprotocol JSON plan for a small liquid-handling experiment and inspect a concise execution summary.
opentrons-liquid-handling-protocol-starter
Use this skill to generate a minimal Opentrons Protocol API transfer script and verify it through the local simulator.
ray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
automated-microscopy-acquisition-starter
Use this starter when a task lands in the Automated microscopy acquisition frontier leaf and the repository has curated resources but no dedicated runtime implementation yet.