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 cxcscmu/SkillLearnBench --skill document-classifiergit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/document-classifier)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/document-classifier"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/document-classifier.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00352 |
| Opus 5 | $0.00008 | $0.00176 |
| Sonnet 5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
document-classifier 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.
What it actually says
Document Classifier Skill
This skill outlines a strategy for classifying documents into predefined categories using keyword frequency and priority.
Subjects and Keywords
- LLM (Large Language Models)
- Keywords: LLM, transformer, GPT, pre-training, inference, attention mechanism, BERT, language model.
- Trapped Ion and Quantum Computing
- Keywords: trapped ion, quantum computer, qubit, entanglement, Paul trap, laser cooling, gate fidelity, Rydberg.
- Black Hole
- Keywords: black hole, event horizon, Schwarzschild, Hawking radiation, gravitational waves, accretion disk, singularity.
- DNA
- Keywords: DNA, genome, sequencing, nucleotide, CRISPR, polymerase, genetic, chromosome, protein synthesis.
- Music History
- Keywords: music, composer, symphony, baroque, classical era, opera, jazz, rhythmic, harmony, melody.
Classification Logic
- Extraction: Extract the first 1000-2000 characters of the document.
- Scoring: Count occurrences of keywords for each category.
- Tie-breaking: If no keywords match or there is a tie, use the "last folder" rule as per user instruction (in this case, Music History if others fail, or simply the most likely fit).
- Verification: Check the title or abstract specifically if the score is low.
Implementation Tip
Use a script or a loop to process files in batches to save time.
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.
- 3d ago First seen · 31 lines · 16 tokens per session scan A 4c122eb25903
document-classifier is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 352 once invoked, about $0.0001 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.
Other skills, from other repositories
pdf-editing
Complete guide for reading and editing PDF documents with PyMuPDF.
image-ocr
Extract text content from images using Tesseract OCR via Python.
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
docx
Word document manipulation with python-docx - handling split placeholders, headers/footers, nested tables.
xlsx-parsing
Read Microsoft Excel (.xlsx) files robustly with openpyxl (or pandas). Covers multi-sheet workbooks, header rows, empty cells, merged cells, comma-separated list cells, and converting a sheet to a list-of-dicts the rest of your code can consume. Use when a task input or reference document is an .xlsx file rather than…
exoplanet-workflows
General workflows and best practices for exoplanet detection and characterization from light curve data. Use when planning an exoplanet analysis pipeline, understanding when to use different methods, or troubleshooting detection issues.