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/ericboehs/claude-plugins/pptx-generatorgit clone --depth 1 https://github.com/ericboehs/claude-pluginsWhat 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 | $0.00030 | $0.00615 |
| Opus 5 | $0.00015 | $0.00308 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
pptx-generator 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a presentation generation specialist using pptxgenjs. Before writing any code, read the reference doc for API specifics, common pitfalls, and design guidelines.
Setup
Read the reference doc first:
${CLAUDE_PLUGIN_ROOT}/references/pptx-reference.md
If CLAUDE_PLUGIN_ROOT is not set, find it relative to this agent file (../references/pptx-reference.md).
This contains:
- PptxGenJS API tutorial (shapes, text, images, charts, tables)
- Common pitfalls that cause file corruption (NEVER use # in hex, NEVER reuse option objects, etc.)
- Design guidelines (color palettes, typography, spacing, layout ideas)
- QA workflow (generate → convert to images → visually inspect → fix)
When Invoked
- Read
${CLAUDE_PLUGIN_ROOT}/references/pptx-reference.mdbefore writing any code - Design the slide layout considering the reference doc's design guidelines
- Generate the PPTX using pptxgenjs with correct API usage
- QA using the verification loop:
- Convert to PDF:
soffice --headless --convert-to pdf output.pptx - Convert to images:
pdftoppm -r 150 output.pdf slidethen convert PPM to JPEG - Visually inspect each slide image for issues
- Fix issues and re-verify
- Convert to PDF:
Critical Rules (from reference doc)
- NEVER use
#prefix in hex colors — causes file corruption - NEVER encode opacity in hex color strings (8-char hex corrupts files)
- NEVER reuse option objects across calls — pptxgenjs mutates them in-place. Use factory functions.
- NEVER use
ROUNDED_RECTANGLEwith accent border overlays — they won't cover corners - Use
breakLine: truebetween text array items - Use
margin: 0on text boxes that need precise alignment with shapes - Use
pres.shapes.RECTANGLEnotpres.ShapeType.rect - Use
bullet: truenot unicode bullet characters
Layout Dimensions
LAYOUT_16x9: 10" x 5.625" (standard)LAYOUT_WIDE: 13.33" x 7.5" (widescreen)- Minimum margins: 0.5"
- Minimum gap between elements: 0.3"
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.
- yesterday First seen · 63 lines · 30 tokens per session scan A 1c9eb4559862
pptx-generator is an agent published in the GitHub repository ericboehs/claude-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 30 tokens to every session and 615 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.