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/chacosoldier/compabob/document-exportnpx skills add chacosoldier/compabob --skill document-exportgit clone --depth 1 https://github.com/chacosoldier/compabobWhat 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 | $0.00072 | $0.01275 |
| Opus 5 | $0.00036 | $0.00638 |
| Sonnet 5 | $0.00014 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
document-export 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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Export
Turn content into a real office file: a PDF, an Excel workbook, or a Word document. The skill ships three helper scripts that do the file writing deterministically; your job is to assemble the content and call the right one.
These scripts use the Python standard library only, so there is nothing to install for Excel and Word. PDF needs a browser or a PDF tool on the machine (the script finds it, or tells the user what to install).
Save every output to reports/ as YYYY-MM-DD-<slug>.<ext>, then tell the user
the path.
PDF is produced by rendering an HTML file. Two cases:
- Rich, visual page (architecture, dashboard, comparison): use the
visual-explainerskill to build the HTML, then convert it. - Plain document (a letter, a report, a write-up): wrap the content in this
minimal template and save it as an
.htmlfile:
<!DOCTYPE html>
<html><head><meta charset="utf-8"><title>TITLE</title>
<style>
@page { margin: 2cm; }
body { font: 11pt/1.55 -apple-system, "Segoe UI", Roboto, sans-serif;
color: #1a1a1a; max-width: 46em; margin: 0 auto; }
h1, h2, h3 { line-height: 1.25; }
h1 { font-size: 1.8em; } h2 { font-size: 1.35em; margin-top: 1.6em; }
table { border-collapse: collapse; width: 100%; }
th, td { border: 1px solid #ccc; padding: 6px 10px; text-align: left; }
code { background: #f4f4f4; padding: 1px 4px; border-radius: 3px; }
</style></head><body>
<!-- CONTENT -->
</body></html>
Then convert:
python3 .claude/skills/document-export/to_pdf.py <input.html> reports/<YYYY-MM-DD>-<slug>.pdf
It tries headless Chrome first, then weasyprint, then wkhtmltopdf. If it reports that no engine is found, relay its install hint to the user; do not try to work around it.
Excel (.xlsx)
Build a JSON spec, write it to a temporary file, and run the writer.
Spec shape:
{
"sheets": [
{
"name": "Results",
"header": true,
"rows": [["Name", "Score"], ["Alice", 90], ["Bob", 85]],
"widths": [24, 10]
}
]
}
What ships with it
3 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.
- 2d ago First seen · 136 lines · 72 tokens per session scan A 6511e590b9a1
document-export is a skill published in the GitHub repository chacosoldier/compabob (32 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,275 once invoked, about $0.0004 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
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.