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 skills/team-commonly/commonly/pandic-officenpx skills add Team-Commonly/commonly --skill pandic-officegit clone --depth 1 https://github.com/Team-Commonly/commonlyWrote 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/team-commonly/commonly/pandic-office)<a href="https://agentmods.dev/skills/team-commonly/commonly/pandic-office"><img src="https://agentmods.dev/badge/skills/team-commonly/commonly/pandic-office.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 | $0.00059 | $0.00694 |
| Opus 5 | $0.00030 | $0.00347 |
| Sonnet 5 | $0.00012 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
pandic-office scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pandic-office — Markdown → PDF / DOCX / EPUB / HTML via pandoc
Pandoc is installed at /usr/bin/pandoc. The XeLaTeX engine (xelatex) is
installed for PDF output. Both work non-interactively in the agent workspace.
Common conversions
# Markdown → PDF (default LaTeX engine)
pandoc input.md -o output.pdf --pdf-engine=xelatex
# Markdown → DOCX (Word document)
pandoc input.md -o output.docx
# Markdown → EPUB (e-book)
pandoc input.md -o output.epub
# Markdown → standalone HTML
pandoc input.md -o output.html --standalone
Producing a one-page brief
cat > /workspace/$(basename "$PWD")/brief.md <<'EOF'
# Q1 Engineering Brief
## Highlights
- Shipped feature X
- Closed Y bugs
## Risks
- Z dependency upgrade pending
EOF
pandoc /workspace/$(basename "$PWD")/brief.md \
-o /workspace/$(basename "$PWD")/brief.pdf \
--pdf-engine=xelatex \
-V geometry:margin=1in \
-V fontsize=11pt
Useful flags
| Flag | Effect |
|---|---|
--toc |
Insert a table of contents |
-V geometry:margin=1in |
Set page margins |
-V fontsize=11pt |
Set body font size |
--number-sections |
Auto-number headings |
--metadata title="..." |
Set document title |
-o file.pdf |
Output filename + format (inferred from extension) |
After producing the file
Attach it to chat using the commonly_attach_file tool (a kernel verb):
commonly_attach_file({
podId: "<the pod>",
filePath: "brief.pdf", // workspace-relative
message: "Q1 brief attached."
})
The file path must stay inside /workspace/<accountId>/ — .. and absolute
paths outside the workspace are rejected.
Troubleshooting
- "xelatex not found" — pandoc fell back to a missing TeX engine. Always
pass
--pdf-engine=xelatex. - "Could not convert image" — embedded images need to be local file paths inside the workspace, not http URLs (unless you pre-fetch them).
- Tables render badly in PDF — add
--variable=tables:trueand use simple Markdown table syntax (no merged cells).
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.
- 4d ago First seen · 88 lines · 59 tokens per session scan A 17269f3dd7e6
pandic-office is a skill published in the GitHub repository Team-Commonly/commonly (1,325 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 694 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 2026-08-30.
Other skills, from other repositories
handoff
Compact the current conversation into a handoff document for another agent to pick up.
pdf-reader
PDF content extraction and analysis specialist.
linear-bug-triage
Use this skill after a bug or regression candidate has measured evidence to document them within linear.
svg-chart
Render data into a standalone SVG chart file — bar, line, or pie. Use when the user provides numbers (inline, JSON, or CSV) and asks for a chart, graph, plot, trend, comparison, breakdown, or any visual summary of the data. Produces a self-contained .svg viewable in any browser; no external libraries required.
doc-gen
Generate documentation from source code — docstrings, READMEs, API references. Triggers on: generate docs, write documentation, document this, create README, API docs, doc-gen.
anomalia
Operate Anomalia (social media AI autopilot) via MCP tools or the anomalia CLI: brands, posts, plans, studio, SEO/GEO, blog, and AI chat. Use when the user mentions Anomalia, anomalia.so, approving social posts, editorial plans, SEO/GEO audits, or managing brand content from an agent.