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 agents/rehglab/arcdeck/09-image-table-filtergit clone --depth 1 https://github.com/RehgLab/ArcDeckWhat 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 | $0.00940 |
| Opus 5 | $0.00000 | $0.00470 |
| Sonnet 5 | $0.00000 | $0.00188 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
09-image-table-filter 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 9: Image/Table Filter
Role
Filters the extracted images and tables from the PDF, keeping only those that are relevant and high-quality for the presentation. Removes irrelevant, decorative, or low-quality visuals. Keeps at most 5 images and 5 tables. Also identifies slides that will need programmatic visual elements (diagrams, infographics) because they lack matching figures.
Position in Pipeline
- Phase: 3 (Slide Generation)
- Depends on: A1 output (markdown.md), A2 output (images.json, tables.json), final_outline.json
- Produces for: A10 (Figure Matcher), A11 (Slide Deck Constructor)
- LLM Required: Yes
Inputs
| Input | Source | Format |
|---|---|---|
| Raw content | workspace/markdown.md or structured outline |
JSON/text |
| Image metadata | workspace/images.json |
JSON dict |
| Table metadata | workspace/tables.json |
JSON dict |
| Final outline | workspace/final_outline.json |
JSON (for slide count estimation) |
Prompt Template
- File:
prompts/pipeline/image_table_filter_agent.yaml - Format: Jinja2 template (
{{ variable }}syntax) - System Message: From the yaml
system_promptfield:"You are an assistant that reviews a presentation deck's JSON layout (json_content), along with corresponding image_information and table_information. Your task is to filter out any image or table entries that are irrelevant..."
Template Variables (Jinja2)
| Variable | Source | Description |
|---|---|---|
{{ json_content }} |
Paper outline / raw content | JSON string of the paper content structure |
{{ image_information }} |
Contents of images.json | JSON string of image metadata |
{{ table_information }} |
Contents of tables.json | JSON string of table metadata |
Prompt Assembly
- Load the yaml file
- Read
system_promptfield -> use as system message - Read
templatefield -> render Jinja2 with the three variables - The rendered template becomes the user message
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 · 97 lines · 0 tokens per session scan A 17cefb6ec28c
09-image-table-filter is an agent published in the GitHub repository RehgLab/ArcDeck (49 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 940 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 agents, from other repositories
html_to_pdf_system_prompt
You are an "HTML slide export agent." Your job is not to design pages. Your job is to export HTML into a stable, reviewable PDF and produce preview images and export logs.
page1-validator
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
product-extraction
Extracts structured product data (name, brand, price, SKU, vendor) from screenshots, PDFs, and catalog images. Use when the user provides images/documents in for-ai/ (ideally vendor-subfoldered under for-ai/catalogs/).
pdf-converter
너는 마크다운 → PDF 변환 책임자다. 3단계 산출물 report.md를 같은 폴더의 report.pdf로 변환한다.
Demonstrate
Agent for demonstrating VS Code features.