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 skills add dfk1352/LibreOffice-skills --skill libreoffice-writergit clone --depth 1 https://github.com/dfk1352/LibreOffice-skillsWrote 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/dfk1352/libreoffice-skills/libreoffice-writer)<a href="https://agentmods.dev/skills/dfk1352/libreoffice-skills/libreoffice-writer"><img src="https://agentmods.dev/badge/skills/dfk1352/libreoffice-skills/libreoffice-writer/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/dfk1352/libreoffice-skills/libreoffice-writer"><img src="https://agentmods.dev/badge/skills/dfk1352/libreoffice-skills/libreoffice-writer.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 | $0.00050 | $0.02264 |
| Opus 5 | $0.00025 | $0.01132 |
| Sonnet 5 | $0.00010 | $0.00453 |
| Haiku 4.5 | $0.00005 | $0.00226 |
Grade A, and why
libreoffice-writer 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 11d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibreOffice Writer
Use the bundled writer modules for UNO-backed Writer document work.
All paths must be absolute. Bundled modules live under scripts/ in this
skill directory, so set PYTHONPATH=<skill_base_dir>/scripts.
If setup or runtime issues appear, check references/troubleshooting.md.
API Surface
# Non-session utilities
create_document(path, source=None) # source: path to .md file to import
export_document(path, output_path, export_format) # formats: "pdf", "docx", "md"
snapshot_page(doc_path, output_path, page=1, dpi=150)
# Session (primary editing API)
WriterSession(path) -> context manager
WriterSession methods:
read_text(target: WriterTarget | None = None) -> str
insert_text(text, target: WriterTarget | None = None)
replace_text(target: WriterTarget, new_text)
delete_text(target: WriterTarget)
format_text(target: WriterTarget, formatting: TextFormatting)
insert_table(rows, cols, data=None, name=None, target: WriterTarget | None = None)
update_table(target: WriterTarget, data)
delete_table(target: WriterTarget)
insert_image(image_path, width=None, height=None, name=None, target: WriterTarget | None = None)
update_image(target: WriterTarget, image_path=None, width=None, height=None)
delete_image(target: WriterTarget)
insert_list(items: list[ListItem], ordered: bool, target: WriterTarget | None = None)
replace_list(target: WriterTarget, items: list[ListItem], ordered: bool | None = None)
delete_list(target: WriterTarget)
set_metadata(values: dict[str, str])
get_metadata() -> dict[str, str]
patch(patch_text, mode="atomic") -> PatchApplyResult
export(output_path, export_format)
reset()
close(save=True)
# Standalone patch utility
patch(path, patch_text, mode="atomic") -> PatchApplyResult
Structured Targets: WriterTarget
from writer import WriterTarget
WriterTarget(
kind="text" | "insertion" | "table" | "image" | "list",
text=None,
after=None,
before=None,
occurrence=None,
name=None,
index=None,
)
What ships with it
14 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.
- references/troubleshooting.md 3.9 KB
- scripts/colors.py 4.6 KB runs code
- scripts/constants.py 180 B runs code
- scripts/exceptions.py 748 B runs code
- scripts/patch_base.py 12 KB runs code
- scripts/session.py 2.6 KB runs code
- scripts/uno_bridge.py 9.1 KB runs code
- scripts/writer/__init__.py 554 B runs code
- scripts/writer/core.py 3.4 KB runs code
- scripts/writer/exceptions.py 2.5 KB runs code
- scripts/writer/patch.py 9.4 KB runs code
- scripts/writer/session.py 19 KB runs code
- scripts/writer/snapshot.py 5.6 KB runs code
- scripts/writer/targets.py 15 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.
- 11d ago First seen · 296 lines · 50 tokens per session scan A 6e09d91512cf
libreoffice-writer is a skill published in the GitHub repository dfk1352/LibreOffice-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 2,264 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
add-pdf-report
Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when present, expo-sharing.
add-sharepoint
Adds SharePoint Online connector to a Power Apps code app. Use when reading lists, managing documents, or integrating with SharePoint sites. Can also create new SharePoint lists.
add-pdf-viewer
Internal implementation skill invoked by /add-native for native PDF control workflows. Handles HTTPS and file URI PDF viewing with @microsoft/power-apps-native-pdf-viewer 0.2.9+.
add-excel
Adds Excel Online (Business) connector to a Power Apps code app. Use when reading or writing Excel workbook data from OneDrive or SharePoint.
add-onedrive
Adds OneDrive for Business connector to a Power Apps code app. Use when uploading, downloading, listing, or managing files in OneDrive.
data-management-plan
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…