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/davidroliverba/architectkb/document-extractnpx skills add DavidROliverBA/ArchitectKB --skill document-extractgit clone --depth 1 https://github.com/DavidROliverBA/ArchitectKBWrote 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/davidroliverba/architectkb/document-extract)<a href="https://agentmods.dev/skills/davidroliverba/architectkb/document-extract"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/document-extract.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 | $0.00000 | $0.00900 |
| Opus 5 | $0.00000 | $0.00450 |
| Sonnet 5 | $0.00000 | $0.00180 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
document-extract 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/document-extract
Extract and analyse content from scanned documents, PDFs, and document images using Sonnet sub-agents.
Usage
/document-extract <file-path>
/document-extract +Attachments/meeting-whiteboard.jpg
/document-extract +Attachments/spec-document.pdf
/document-extract +Attachments/handwritten-notes.png --type "meeting notes"
Instructions
This skill uses Sonnet model sub-agents for comprehensive document analysis and text extraction.
Phase 1: Document Loading
- Verify the file exists at the specified path
- Identify document type (PDF, image, photo of document)
- Note any context about document purpose
Phase 2: Comprehensive Analysis (Sonnet Sub-Agents)
Launch these sub-agents using model: "sonnet":
Agent 1: Text Extraction (Sonnet)
Task: Extract all text content from the document
- Read the file using the Read tool
- Perform comprehensive OCR on all visible text
- Preserve structure (headings, paragraphs, lists)
- Handle multiple columns if present
- Extract text from tables maintaining structure
- Note any text that is unclear or uncertain
Return: Complete text extraction with structure preserved
Agent 2: Structure Analysis (Sonnet)
Task: Analyse document structure and formatting
- Read the file
- Identify document type (letter, form, spec, notes, etc.)
- Map section hierarchy
- Identify tables, lists, and special formatting
- Note headers, footers, page numbers
- Identify logos, stamps, signatures
Return: Document structure map
Agent 3: Content Classification (Sonnet)
Task: Classify and categorise the content
- Read the file
- Determine document purpose
- Identify key entities (people, projects, dates, systems)
- Extract action items or tasks
- Find decisions or commitments
- Note any deadlines or dates mentioned
- Identify references to YourOrg projects or systems
Return: Classified content with entity extraction
Agent 4: Quality Assessment (Sonnet)
Task: Assess extraction quality and completeness
- Read the file
- Evaluate image/scan quality
- Identify areas with low confidence extraction
- Note any missing or obscured content
- Assess if re-scan might be needed
- Check for multiple pages
Return: Quality report with confidence scores
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.
- 4d ago First seen · 165 lines · 0 tokens per session scan A 71ce98662ae6
document-extract is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 900 tokens. 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.