Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leiverkus/open-document-skillsnpx agentmods add skills/leiverkus/open-document-skills/odgWrote 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/skills/leiverkus/open-document-skills/odg)<a href="https://agentmods.dev/skills/leiverkus/open-document-skills/odg"><img src="https://agentmods.dev/badge/skills/leiverkus/open-document-skills/odg/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leiverkus/open-document-skills/odg"><img src="https://agentmods.dev/badge/skills/leiverkus/open-document-skills/odg.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.03136 |
| Opus 5 | $0.00028 | $0.01568 |
| Sonnet 5 | $0.00011 | $0.00627 |
| Haiku 4.5 | $0.00006 | $0.00314 |
Grade A, and why
odg 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ODG creation, editing, and analysis
Overview
An .odg file is an OpenDocument ZIP package for vector drawings, diagrams, and LibreOffice Draw documents. Important package files:
mimetype- should be the first ZIP entry and stored uncompressed asapplication/vnd.oasis.opendocument.graphicscontent.xml- pages, shapes, connectors, text boxes, images, and drawing contentstyles.xml- drawing, text, page, and graphic stylesmeta.xml- document metadatasettings.xml- application settingsMETA-INF/manifest.xml- package manifestPictures/...- embedded raster or vector media
Quick Reference
| Task | Preferred approach |
|---|---|
| Create simple drawing/diagram | Generate ODG package XML directly |
| Create branded/repeated diagram | Start from an .odg template and edit XML |
| Use SVG-first | Only when portable vector output matters more than Draw editability |
| Extract visible text | Use scripts/extract_text.py or parse content.xml |
| Inspect shapes/geometry | Use scripts/extract_shapes.py |
| Convert ODG to PDF/SVG/PNG | LibreOffice headless export |
| Visual QA | Export to PDF/PNG/SVG and inspect the rendered output |
Tool Checks
Before starting a real ODG task, check available tools:
which pandoc
Resolve the LibreOffice command as described in docs/soffice-resolver.md.
Reading and Inspecting
For raw package inspection:
unzip -l input.odg
python -m zipfile -e input.odg unpacked_odg
Drawing content is usually in content.xml. Inspect:
draw:pagefor pages/canvasesdraw:custom-shape,draw:rect,draw:ellipse,draw:path,draw:line, anddraw:connectorfor vector objectsdraw:frameanddraw:imagefor embedded mediatext:pandtext:spanfor visible text labelsstyle:stylereferences for fill, stroke, text, and positioning behavior
Use an XML parser with namespace support. Do not use regex for XML edits.
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- LICENSE.txt 1.0 KB
- scripts/add_gluepoint.py 2.9 KB runs code
- scripts/add_image.py 2.5 KB runs code
- scripts/connect_shapes.py 3.3 KB runs code
- scripts/create_minimal_odg.py 14 KB runs code
- scripts/extract_shapes.py 1.4 KB runs code
- scripts/extract_text.py 1.2 KB runs code
- scripts/group_shapes.py 2.3 KB runs code
- scripts/inspect_package.py 2.2 KB runs code
- scripts/list_structure.py 3.5 KB runs code
- scripts/list_styles.py 1.5 KB runs code
- scripts/odg_common.py 10 KB runs code
- scripts/pack_fodg.py 548 B runs code
- scripts/pack_odg.py 547 B runs code
- scripts/render.py 2.7 KB runs code
- scripts/replace_text.py 1.2 KB runs code
- scripts/ungroup.py 2.2 KB runs code
- scripts/unpack_fodg.py 535 B runs code
- scripts/validate_refs.py 5.6 KB runs code
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 · 314 lines · 56 tokens per session scan A d58e2bfda500
odg is a skill published in the GitHub repository leiverkus/open-document-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 3,136 once invoked, about $0.0003 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 skills, from other repositories
pdf-design
Designs PDF reports and proposals from HTML with previews and branding. Use to create, export, or securely upload a PDF.
document-design
Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.
design-export-repair
Fixes broken decks/PDFs exported from Claude's "Design" feature (or similar AI deck generators) — cut-off or clipped text, wrong/substituted fonts, and corrupted .pptx package structure that shows up only once you export to PDF, not while looking at it in the app. Use this skill whenever the user uploads a zip, .pptx…
brand-consistency-checker
Scan documents and slides for off-brand colors, fonts, and logos. Validate against brand guidelines and suggest corrections.
strategy-consulting-visualization
Use when turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics, process flows, timelines, benchmarks, waterfall charts, or data-backed visual specs for any audience.
convert-mermaid
Translate .mmd diagram files into PNG images with configurable resolution (retina/HQ/scale), supporting rasterization (raster, rasterize, rasterization). V2 includes L5 Delegated Constraint Verification via verifypng for strict binary linting and Puppeteer-based rendering.