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 shaharsha/claude-skills --skill office-rendergit clone --depth 1 https://github.com/shaharsha/claude-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/shaharsha/claude-skills/office-render)<a href="https://agentmods.dev/skills/shaharsha/claude-skills/office-render"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/office-render/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/shaharsha/claude-skills/office-render"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/office-render.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 | $0.00112 | $0.01582 |
| Opus 5 | $0.00056 | $0.00791 |
| Sonnet 5 | $0.00022 | $0.00316 |
| Haiku 4.5 | $0.00011 | $0.00158 |
Grade A, and why
office-render 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Office Render (macOS, real Microsoft Office)
Overview
To verify how a .docx/.pptx/.xlsx looks, render it with the installed
Microsoft Office app, not LibreOffice. LibreOffice substitutes fonts and
re-flows complex layouts — it renders a 3-across team grid as a vertical list and
swaps the typeface, so what you "see" isn't what the user sees. Word/PowerPoint
produce the exact, pixel-faithful page; then convert the PDF to images you can read.
Pipeline: Office file → (real Word/PowerPoint/Excel) → PDF → (pdftoppm) → page JPGs.
When to use
- "Show me / screenshot / preview this Word doc (or deck, or spreadsheet)."
- Visually QA a
.docx/.pptxyou just generated (python-docx, python-pptx) — confirm fonts, tables, images, and slide layout look right. - A LibreOffice render looks wrong (substituted font, broken table/grid, RTL flipped) and you need the true rendering.
- Read a doc whose layout matters (not just text — for text,
markitdown/pandocis fine).
Skip when you only need the text (use pandoc -t plain / python -m markitdown), or you're not on macOS / Office isn't installed (fall back to soffice --headless --convert-to pdf, accepting lower fidelity).
Usage
uv run --no-project --with docx2pdf python3 ~/.claude/skills/office-render/scripts/office_render.py \
"/path/to/file.pptx" --out /tmp/render --dpi 150
--no-project is not optional cosmetics: without it, uv run tries to install
the surrounding directory as a project, and if the CWD (or any parent) holds a
pyproject.toml with no [project] table — common in tool-only repos — it aborts
with No 'project' table found before the script ever runs. --no-project tells
uv to just build an ephemeral env from --with and ignore whatever project it's
sitting inside. Harmless when there's no pyproject either, so always pass it.
It writes file.pdf + file-1.jpg, file-2.jpg, … into --out and prints the
paths. Then Read the JPGs. Options: --format png, --pdf-only, --dpi N
(150 is plenty; the page is small on screen). Works for .docx, .pptx, .xlsx.
What ships with it
2 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.
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.
- 12d ago First seen · 91 lines · 112 tokens per session scan A 0593bb01b013
office-render is a skill published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 14d ago), licensed MIT. It adds 112 tokens to every session and 1,582 once invoked, about $0.0006 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.