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/10-slide-composergit clone --depth 1 https://github.com/RehgLab/ArcDeckWrote 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/agents/rehglab/arcdeck/10-slide-composer)<a href="https://agentmods.dev/agents/rehglab/arcdeck/10-slide-composer"><img src="https://agentmods.dev/badge/agents/rehglab/arcdeck/10-slide-composer.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 | $0.02281 |
| Opus 5 | $0.00000 | $0.01141 |
| Sonnet 5 | $0.00000 | $0.00456 |
| Haiku 4.5 | $0.00000 | $0.00228 |
Grade A, and why
10-slide-composer 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 5d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 10: Slide Composer
Role
Holistic slide plan creation — simultaneously matches figures to slides, selects templates, writes content, and designs visual elements. This is the first agent in the aesthetic pipeline: it transforms the narrative outline into a concrete, visually-rich slide plan.
Claude Code executes this agent directly — no external API calls. Read all inputs, reason about layout and content, and produce slide_plan.json.
Position in Pipeline
- Phase: 6 (Slide Composition)
- Depends on: A8 output (
final_outline.json), A9 output (images_filtered.json,tables_filtered.json), A3 output (commitments.md), A4 output (rst/*/paragraphs.json), A1 output (markdown.md) - Produces for: A11 (Design Critic)
- LLM Required: Yes (Claude Code itself)
Inputs
| Input | Source | Format |
|---|---|---|
workspace/final_outline.json |
A8 (Narrative Judge) | JSON array of slide groupings |
workspace/images_filtered.json |
A9 (Image/Table Filter) | JSON dict of filtered images with captions, dims |
workspace/tables_filtered.json |
A9 (Image/Table Filter) | JSON dict of filtered tables with captions, dims |
workspace/commitments.md |
A3 (Commitment Builder) | Markdown with metadata + guidance |
workspace/rst/*/paragraphs.json |
A4 (Discourse Parser) | JSON dict mapping paragraph_id → text |
workspace/markdown.md |
A1 (PDF Preprocessor) | Full paper text |
Step-by-Step Instructions
Step 1: Read and Understand All Inputs
- Read
workspace/final_outline.json. Each entry has:slide_number,section,section_title,title,paragraphs[](paragraph IDs),rationale. - Read
workspace/images_filtered.json. Each entry has:caption,page_no,image_path,width,height,figure_aspect. - Read
workspace/tables_filtered.json. Same structure as images. - Read
workspace/commitments.md. Extract from the Snapshot section:title— paper titleauthor— author namespublish date— publication venue/yearorganization— affiliations
- Read all
workspace/rst/*/paragraphs.jsonfiles. Build a lookup:paragraph_id → full_text. - Skim
workspace/markdown.mdfor any additional context.
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.
- 5d ago First seen · 210 lines · 0 tokens per session scan A 20cd19e19381
10-slide-composer is an agent published in the GitHub repository RehgLab/ArcDeck (49 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,281 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.