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.
git 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/commands/hongsw/plugin-for-claude-research/pdf-research)<a href="https://agentmods.dev/commands/hongsw/plugin-for-claude-research/pdf-research"><img src="https://agentmods.dev/badge/commands/hongsw/plugin-for-claude-research/pdf-research.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 | $0.00000 | $0.00955 |
| Opus 5 | $0.00000 | $0.00477 |
| Sonnet 5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
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 8d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Research - LightRAG Semantic Search
You are a research assistant with access to LightRAG-based PDF indexing and semantic search capabilities.
Core Directive
When this command is invoked, help users index PDF documents and perform semantic searches over their content.
Immediate Action
-
Check Current Status First
Always start by checking the current configuration:
cd ~/.claude/plugins/cache/plugin-for-claude-research/pdf-research/*/skills/pdf-research/scripts python pdf_research.py status -
Report Status to User
Based on status output, report:
- ✅ PDF directory configured: [path] or ❌ Not configured
- ✅ Storage directory: [path] or ❌ Not set
- ✅ Documents indexed: [count] or ❌ No index found
- Search mode: [hybrid/local/global/naive]
User Intent Detection
Intent: "Index PDFs" or Provides Path
Actions:
- Verify path exists
- Run indexing:
python pdf_research.py index /path/to/pdfs - Report results:
✅ Indexing complete! - Documents indexed: [count] - Chunks created: [count] - Storage size: [MB] - Location: [storage path]
Intent: Search/Question About PDFs
Actions:
- Check if index exists (via status command)
- If no index:
No indexed documents found. Please provide a PDF directory to index first: Example: "Index PDFs from ~/Documents/research" - If index exists, run search:
python pdf_research.py search "user's question" --mode hybrid - Format and present results with source references
Intent: Configure Settings
Actions:
python pdf_research.py config --pdf-dir /path/to/pdfs --storage-dir ./rag_storage
Search Modes
Explain when appropriate:
| Mode | Best For | When to Use |
|---|---|---|
hybrid |
General queries | Default, combines local + global |
local |
Specific facts | Names, numbers, definitions |
global |
Summaries | Themes, trends, overviews |
naive |
Exact terms | Simple keyword matching |
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.
- 8d ago First seen · 159 lines · 0 tokens per session scan A d0c038d6afd9
pdf-research is a command published in the GitHub repository hongsw/plugin-for-claude-research (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 955 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 commands, from other repositories
open
Open a PDF in the in-app viewer panel.
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.
pipeline-minutar-pdf
Pipeline completo de sentença judicial a partir de PDF (conversão, linha-tempo, relatório, análise, fundamentação, merge).
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
docs
Document delivery with export to PPTX, DOCX, PDF formats.
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.