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 hongsw/plugin-for-claude-research --skill pdf-researchgit clone --depth 1 https://github.com/hongsw/plugin-for-claude-researchWrote 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/hongsw/plugin-for-claude-research/pdf-research)<a href="https://agentmods.dev/skills/hongsw/plugin-for-claude-research/pdf-research"><img src="https://agentmods.dev/badge/skills/hongsw/plugin-for-claude-research/pdf-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hongsw/plugin-for-claude-research/pdf-research"><img src="https://agentmods.dev/badge/skills/hongsw/plugin-for-claude-research/pdf-research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.01132 |
| Opus 5 | $0.00018 | $0.00566 |
| Sonnet 5 | $0.00007 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
pdf-research 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 9d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Research Skill
LightRAG-based PDF document indexing and semantic search for Claude Code research workflows.
Quick Start (For Claude)
When user invokes /pdf-research, Claude should:
- Check status first: Run
python pdf_research.py statusto see current configuration - Auto-index if requested: When user provides a PDF directory, run indexing automatically
- Search queries: Execute searches and return formatted results
Automatic Workflow
# Always run from scripts directory
cd ~/.claude/skills/pdf-research/scripts
# Check current status
python pdf_research.py status
# Index PDFs (when user provides a directory)
python pdf_research.py index /path/to/pdfs
# Search (single query)
python pdf_research.py search "user's question" --mode hybrid
# Interactive search session
python pdf_research.py search
Environment Requirements
Before running commands, ensure:
# Activate Python environment with dependencies
source /path/to/venv/bin/activate # or use system Python with deps installed
# Ensure OpenAI API key is set
export OPENAI_API_KEY=sk-...
Core Capabilities
1. PDF Indexing (index command)
- Extracts text from PDF documents using PyMuPDF
- Creates semantic chunks with metadata
- Builds knowledge graph with entities and relationships
- Generates vector embeddings for semantic search
- Supports incremental indexing (only new files)
2. Semantic Search (search command)
- naive: Simple keyword matching
- local: Focus on specific entities and details
- global: Focus on broad themes and summaries
- hybrid: Combined local + global (recommended)
3. Status Check (status command)
- Shows current configuration
- Lists indexed documents
- Reports storage statistics
4. Configuration (config command)
- Set default PDF directory
- Set default storage directory
- Set default search mode
Claude Integration Protocol
When User Says "Index PDFs" or Provides a Path
- Verify the path exists
- Run:
python pdf_research.py index <path> - Report results (documents indexed, chunks created, storage size)
What ships with it
9 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.
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.
- 9d ago First seen · 176 lines · 36 tokens per session scan A 5b9fea92b32e
pdf-research is a skill published in the GitHub repository hongsw/plugin-for-claude-research (20 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,132 once invoked, about $0.0002 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.