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 agentmods add skills/huggingface/sentence-transformers/train-sentence-transformersnpx skills add huggingface/sentence-transformers --skill train-sentence-transformersgit clone --depth 1 https://github.com/huggingface/sentence-transformersWhat 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 | $0.00146 | $0.02541 |
| Opus 5 | $0.00073 | $0.01270 |
| Sonnet 5 | $0.00029 | $0.00508 |
| Haiku 4.5 | $0.00015 | $0.00254 |
Grade A, and why
train-sentence-transformers 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- train-sentence-transformers — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Train a sentence-transformers Model
This SKILL.md is a router, not a manual. It tells you which references and example scripts to load for your task. The actual content (recommended losses, evaluators, training-script structure, model selection, training-arg knobs, troubleshooting) lives in references/ and scripts/.
Do not synthesize a training script from this file alone. Open the per-type production template (scripts/train_<type>_example.py) and copy it as your starting point. The templates contain load-bearing scaffolding (autocast helper, model-card class, logger silencing list, force=True, seed, TF32, version-compatible imports, named-evaluator metric handling) that prior agent runs have repeatedly missed when rolling their own from a synthesized snippet.
1. Identify the model type
| Tag | Class | What it does | When to pick |
|---|---|---|---|
| [SentenceTransformer] | SentenceTransformer (bi-encoder) |
Maps each input to a fixed-dim dense vector | Retrieval, similarity, clustering, classification, paraphrase mining, dedup |
| [CrossEncoder] | CrossEncoder (reranker) |
Scores (query, passage) pairs jointly |
Two-stage retrieval (rerank top-100 from bi-encoder), pair classification |
| [SparseEncoder] | SparseEncoder (SPLADE) |
Sparse vectors over the vocabulary | Learned-sparse retrieval, inverted-index backends (Elasticsearch / OpenSearch / Lucene) |
| [MultiVectorEncoder] | MultiVectorEncoder (ColBERT) |
One embedding per token, scored with MaxSim | Late-interaction retrieval, recall gains over bi-encoders at higher storage cost, multimodal (ColPali / ColQwen2) |
Tiebreakers when the request is ambiguous: "embedding model" / "vector search" / "similarity" → [SentenceTransformer]. "rerank" / "ranker" / "two-stage" → [CrossEncoder]. "SPLADE" / "sparse" / "inverted index" → [SparseEncoder]. "ColBERT" / "late interaction" / "multi-vector" / "MaxSim" / "ColPali" / "ColQwen" → [MultiVectorEncoder]. If still unclear, ask.
What ships with it
30 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/base_model_selection.md 7.5 KB
- references/dataset_formats.md 6.3 KB
- references/evaluators_cross_encoder.md 5.5 KB
- references/evaluators_multi_vector_encoder.md 6.6 KB
- references/evaluators_sentence_transformer.md 5.8 KB
- references/evaluators_sparse_encoder.md 4.9 KB
- references/hardware_guide.md 5.9 KB
- references/hf_jobs_execution.md 7.1 KB
- references/losses_cross_encoder.md 9.5 KB
- references/losses_multi_vector_encoder.md 10 KB
- references/losses_sentence_transformer.md 11 KB
- references/losses_sparse_encoder.md 5.1 KB
- references/model_architectures.md 9.0 KB
- references/prompts_and_instructions.md 6.4 KB
- references/training_args.md 15 KB
- references/troubleshooting.md 13 KB
- scripts/mine_hard_negatives.py 8.3 KB runs code
- scripts/train_cross_encoder_distillation_example.py 9.2 KB runs code
- scripts/train_cross_encoder_example.py 9.0 KB runs code
- scripts/train_cross_encoder_listwise_example.py 10 KB runs code
- scripts/train_multi_vector_encoder_example.py 8.8 KB runs code
- scripts/train_sentence_transformer_distillation_example.py 12 KB runs code
- scripts/train_sentence_transformer_example.py 7.5 KB runs code
- scripts/train_sentence_transformer_make_multilingual_example.py 12 KB runs code
- scripts/train_sentence_transformer_matryoshka_example.py 7.1 KB runs code
- scripts/train_sentence_transformer_multi_dataset_example.py 9.9 KB runs code
- scripts/train_sentence_transformer_static_embedding_example.py 10 KB runs code
- scripts/train_sentence_transformer_with_lora_example.py 10 KB runs code
- scripts/train_sparse_encoder_distillation_example.py 9.4 KB runs code
- scripts/train_sparse_encoder_example.py 8.1 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.
- yesterday First seen · 110 lines · 146 tokens per session scan A 9bd098d81049
train-sentence-transformers is a skill published in the GitHub repository huggingface/sentence-transformers (19,046 stars, last pushed 4d ago), licensed Apache-2.0. It adds 146 tokens to every session and 2,541 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…