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/Miaoge-Ge/coding-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/plugins/miaoge-ge/coding-agent-skills/deep-learning-expert)<a href="https://agentmods.dev/plugins/miaoge-ge/coding-agent-skills/deep-learning-expert"><img src="https://agentmods.dev/badge/plugins/miaoge-ge/coding-agent-skills/deep-learning-expert/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/miaoge-ge/coding-agent-skills/deep-learning-expert"><img src="https://agentmods.dev/badge/plugins/miaoge-ge/coding-agent-skills/deep-learning-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
deep-learning-expert 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "deep-learning-expert",
"displayName": "Deep Learning Expert",
"version": "1.0.0",
"description": "Model architecture design, training strategies, debugging, and paper interpretation (PyTorch/TensorFlow).",
"author": { "name": "Miaoge-Ge", "email": "[email protected]" },
"homepage": "https://github.com/Miaoge-Ge/coding-agent-skills",
"repository": "https://github.com/Miaoge-Ge/coding-agent-skills",
"license": "MIT",
"keywords": ["deep-learning", "pytorch", "tensorflow", "neural-networks", "training", "cv", "nlp"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 100 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 First seen · 13 lines scan A ee6a2e327e20
deep-learning-expert is a plugin published in the GitHub repository Miaoge-Ge/coding-agent-skills (7 stars, last pushed 4mo ago), 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 2026-08-31.
Other plugins, from other repositories
ai-researcher
Reasons from data generating processes, inductive biases, and compute-data-algorithm trade-offs through train/val/test discipline, seed sweeps, ablation ladders, and standards like NeurIPS reproducibility checklists, model cards, and lm-eval-harness, while treating data leakage (Kapoor & Narayanan taxonomy), benchmark.
cheminformatician
Reasons from Standard InChI identity and RDKit sanitization through ChEMBL pChEMBL harmonization, Morgan/ECFP fingerprints, scaffold splits and applicability domains, while treating tautomer collapse, KNIME-vs-Python canonicalization drift, and random-split QSAR leakage as first-class failure modes.
alterlab-bioinformatics
Genomics, proteomics, and single-cell analysis (Scanpy, BioPython, pysam, ESM) (38 skills).
alterlab-cheminformatics
Chemistry and drug discovery (RDKit, docking, ADMET, mass spec) (12 skills).
alterlab-domain-specific
Quantum computing, geospatial, materials, astronomy, and digital humanities (18 skills).
telnyx-ai
Telnyx AI — LLM inference, chat completions, embeddings, AI assistants, Meeting Bot, conversation insights.