data_processing

A tool for extracting text from PDF files and querying CSV files, which are tables stored as plain text. It can use OCR, a method for reading text from scanned pages.

In plain words
What is it for?
Use it to extract text from PDFs, including scans, and filter, inspect, or summarize data in CSV files.
Why use it?
It removes the need to open documents manually or write data-handling code for straightforward searches and summaries.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/binary16labs/prime-silo/data_processing
Any agent
npx skills add binary16labs/prime-silo --skill data_processing
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo

Made for: Claude Code, Codex.

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 308 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00011 $0.00308
Opus 5 $0.00005 $0.00154
Sonnet 5 $0.00002 $0.00062
Haiku 4.5 $0.00001 $0.00031

Measured 2d ago against content hash 4ce54cbdf67a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data_processing 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 2d 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.

runtime/skills/data_processing/SKILL.md · 27 lines

What it actually says

Usage

Use this skill when analyzing tabular data (CSV) or unstructured PDF documents within the workspace. This gives you the ability to query dataframes via Pandas and extract raw text (including OCR fallback via PyMuPDF/Tesseract) from PDFs.

[!WARNING] While extract_pdf_text is useful for quick, ad-hoc reads, do NOT use this to feed multi-agent swarms or complex analyses for files located in the staging/ directory. Those files must be formally ingested into the Knowledge Graph via a rag_ingest pipeline first.

Tools

  • extract_pdf_text(pdf_path, workspace="default") - Extracts all text from a given PDF file in data_in. Supports fallback OCR.
  • query_csv(csv_path, query, workspace="default") - Query a CSV file using Pandas. The query can be a standard string like "amount > 100" or a dataframe expression like "df.describe()".

Examples

Action: query_csv Action Input: {"csv_path": "financials.csv", "query": "df.head(5)"} Observation: Returns the first 5 rows formatted as a markdown table.

Action: extract_pdf_text Action Input: {"pdf_path": "architecture_diagram.pdf"} Observation: Returns the text content extracted from the document.

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. 2d ago First seen · 27 lines · 11 tokens per session scan A 4ce54cbdf67a

Subscribe to this mod's changes

data_processing is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 11 tokens to every session and 308 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 2026-08-31.