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.
git clone --depth 1 https://github.com/ndif-team/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/plugins/ndif-team/skills/nnsight)<a href="https://agentmods.dev/plugins/ndif-team/skills/nnsight"><img src="https://agentmods.dev/badge/plugins/ndif-team/skills/nnsight/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/plugins/ndif-team/skills/nnsight"><img src="https://agentmods.dev/badge/plugins/ndif-team/skills/nnsight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
nnsight 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 1mo 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
{
"name": "nnsight",
"version": "2.0.0",
"description": "Neural network interpretability with nnsight 0.8 - tracing, intervening, patching, steering, debugging, and remote execution on NDIF",
"author": {
"name": "NDIF Team"
}
}
What it installs
The manifest is a name and a version. 19 skills travel with it, and installing the plugin installs all of them — 2,479 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill causal-tracing A 128 tokens
- Skill model-editing-and-lora A 117 tokens
- Skill probing A 93 tokens
- Skill activation-patching A 94 tokens
- Skill circuit-discovery A 126 tokens
- Skill debugging A 157 tokens
- Skill diffusion-and-multimodal A 115 tokens
- Skill sae-and-dictionary-learning A 113 tokens
- Skill tensor-parallel A 160 tokens
- Skill vllm A 135 tokens
- Skill ablation A 120 tokens
- Skill attention-analysis A 131 tokens
- Skill attribution-patching A 128 tokens
- Skill interp-experiment-design A 103 tokens
- Skill logit-lens A 123 tokens
- Skill model-steering A 135 tokens
- Skill nnsight A 158 tokens
- Skill quantization A 228 tokens
- Skill remote A 115 tokens
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.
- 1mo ago Changed 2898a4f58de9
- 1mo ago First seen · 9 lines scan A da847d8691d8
nnsight is a plugin published in the GitHub repository ndif-team/skills (14 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
medsci-modeling
Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never replaces them.
fiftyone-skills
FiftyOne computer vision dataset management with 80+ operators for import, export, inference, evaluation, visualization, and plugin development.
geoai
18 Agent Skills covering the full geospatial data science lifecycle: data engineering, remote sensing, Earth Engine, deep learning, spatial statistics, geostatistics, terrain, networks, LiDAR, trajectories, change detection, MCDA, PostGIS, cartography, and guarded ArcGIS Pro automation.
geoai-skills
GeoAI-powered skills for Claude Code: inspect geospatial files, download satellite imagery, search STAC catalogs, fetch Overture Maps data, process rasters, run AI object detection, and search session logs.
dominodatalab
Full Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams.
sciagent-skills
Life sciences computational skills for scientific AI agents — 197 skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing.