09-image-table-filter

A presentation-planning step that reviews images and tables extracted from a PDF, a document format often used for research papers, and selects the useful ones. It also marks slides that need diagrams or other visuals created from scratch.

In plain words
What is it for?
Selecting up to five relevant images and five tables for a slide deck, and identifying slides that need diagrams or infographics.
Why use it?
It prevents irrelevant, decorative, or poor-quality figures from cluttering the presentation. It also highlights gaps where the source document has no suitable visual.

Agent

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 agents/rehglab/arcdeck/09-image-table-filter
Clone the repo
git clone --depth 1 https://github.com/RehgLab/ArcDeck
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 940 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 $0.00000 $0.00940
Opus 5 $0.00000 $0.00470
Sonnet 5 $0.00000 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 3d ago against content hash 17cefb6ec28c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

arcdeck-skill/agents/09-image-table-filter.md · 97 lines

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_prompt field:

    "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

  1. Load the yaml file
  2. Read system_prompt field -> use as system message
  3. Read template field -> render Jinja2 with the three variables
  4. The rendered template becomes the user message

Read the full file on GitHub · 97 lines

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. 3d ago First seen · 97 lines · 0 tokens per session scan A 17cefb6ec28c

Subscribe to this mod's changes

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.