nlp

nlp is a skill for Claude Code, Codex from ericrisco/rsc-harness. It costs 142 tokens per session (3,515 once invoked), scanned A, original, MIT.

A guide for working with natural-language processing, the field of making computers handle human language. It covers splitting text into tokens, choosing transformer model types, and selecting useful evaluation measures for tasks such as classification, named-entity recognition, and summarisation.

In plain words
What is it for?
Use it to choose tokenisers and transformer architectures, investigate text fragmentation, and evaluate language classification, entity extraction, or summarisation systems.
Why use it?
It helps explain poor results or unexpectedly high token costs by separating problems in tokenisation, model choice, and evaluation. It also helps avoid using a score that does not match the task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to choose tokenisers and transformer architectures, investigate text fragmentation, and evaluate language classification, entity extraction, or summarisation systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ericrisco/rsc-harness/nlp
Install

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.

Any agent
npx skills add ericrisco/rsc-harness --skill nlp
Clone the repo
git clone --depth 1 https://github.com/ericrisco/rsc-harness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for nlp

README.md
[![agentmods](https://agentmods.dev/badge/skills/ericrisco/rsc-harness/nlp.svg)](https://agentmods.dev/skills/ericrisco/rsc-harness/nlp)
Your own site
<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/nlp"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/nlp.svg" alt="Measured on agentmods" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.03515
Opus 5 $0.00071 $0.01758
Sonnet 5 $0.00028 $0.00703
Haiku 4.5 $0.00014 $0.00351

Measured 3d ago against content hash 13c2f1cd66be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

nlp 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 3d 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.

skills/nlp/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nlp — tokenize the text, pick the model type, pick the metric

You own the language-modeling discipline: how raw text becomes tokens, which transformer architecture fits a task, and which metric actually tells you whether it worked. When the question is "which tokenizer," "BERT or GPT or T5 for this," "why does my Catalan text cost 3× the tokens," or "is this BLEU score meaningful," this is the skill. You stop at retrieval, the RAG loop, prompt wording, and the training step itself — those route out (below).

Route out first (loud — do not duplicate these)

Decision: model type per task (get this right before anything else)

Pick the architecture from the task's shape, not from what is trendy. A decoder LLM can technically classify, but a fine-tuned encoder is smaller, faster, cheaper, and usually more accurate on a fixed-label task.

Task shape Architecture Why Example families*
Understand / label a whole input (classification, NER, extractive QA, similarity) Encoder (bidirectional) Attends to the full sentence both directions; cheap to fine-tune and to serve BERT, RoBERTa, DistilBERT, ModernBERT
Free-form generation, chat, few-shot Decoder (autoregressive) Attends only to prior tokens; predicts the next token GPT-style, Llama, Gemma, Qwen
Transform input → new text (summarize, translate, generative QA) Encoder-decoder / seq2seq Encoder reads all of the source, decoder writes conditioned on it T5 / FLAN-T5, BART, mT5

Read the full file on GitHub · 226 lines

Files

What ships with it

4 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.

Changes

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.

  1. 3d ago First seen · 226 lines · 142 tokens per session scan A 13c2f1cd66be

Subscribe to this mod's changes

nlp is a skill published in the GitHub repository ericrisco/rsc-harness (65 stars, last pushed yesterday), licensed MIT. It adds 142 tokens to every session and 3,515 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 2026-09-03.

Related

Other skills, from other repositories

huggingface-tokenizers

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance…

davila7/claude-code-templates · 75 tokens

huggingface-tokenizers

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance…

OpenLAIR/dr-claw · 75 tokens

huggingface-tokenizers

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance…

synthetic-sciences/openscience · 75 tokens

huggingface-transformers

Operational skill for Hugging Face Transformers: pipelines, tokenizers, fine-tuning, and inference with AutoModel APIs.

alivirgo/Major-AI-Skills · 30 tokens

research-huggingface-tokenizers

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alig...

GrayCodeAI/starling · 52 tokens

digital-health-clinical-asr-eval

Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipasource diagnostic). Not for ASR auth (/riva-asr).

NVIDIA/skills · 51 tokens