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 ncepuee/PDFCompress --skill pdf-compressgit clone --depth 1 https://github.com/ncepuee/PDFCompressWrote 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/ncepuee/pdfcompress/pdf-compress)<a href="https://agentmods.dev/skills/ncepuee/pdfcompress/pdf-compress"><img src="https://agentmods.dev/badge/skills/ncepuee/pdfcompress/pdf-compress.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 5.1 | $0.00053 | $0.00359 |
| Opus 5 | $0.00026 | $0.00179 |
| Sonnet 5 | $0.00011 | $0.00072 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
pdf-compress 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 7d 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.
What it actually says
PDFCompress
Use the pdfcompress MCP tools when available; otherwise run the CLI.
Workflow
-
Analyze the source before changing anything:
pdfcompress analyze "input.pdf" --json -
Preserve the source and write to a different output path. For official, award, tender, or archival material, start with
archive-safe; otherwise usehigh. -
If the user specifies a size limit, pass
--target-size-mb. The tool reopens the original for every progressively stronger preset, avoiding cumulative JPEG loss.pdfcompress compress "input.pdf" "output.pdf" --preset archive-safe --target-size-mb 4 --json -
Report the output path, source/output byte sizes, reduction percentage, selected preset, verification status, and all warnings.
Safety boundaries
- Never use the same path for input and output.
- Do not overwrite an existing output unless the user explicitly authorizes it.
- Rewriting invalidates digital signatures. Stop on signed PDFs unless the user explicitly accepts signature loss and the signed original remains preserved.
- Keep text checking enabled unless extraction is unavailable or the user explicitly chooses structural-only verification.
- Treat
text_equal: false, changed page counts, or changed page boxes as failure. - A target-size miss is not permission to rasterize whole pages or remove fonts, bookmarks, attachments, annotations, or visible layers.
What ships with it
1 file 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.
- 7d ago First seen · 36 lines · 53 tokens per session scan A b17d1d24041f
pdf-compress is a skill published in the GitHub repository ncepuee/PDFCompress (1 stars, last pushed 11d ago), licensed MIT. It adds 53 tokens to every session and 359 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
paper-writing
Write and typeset formal documents — academic papers, reports, articles — using Markdown + Pandoc and LaTeX. Convert between formats (md↔pdf↔docx↔tex), manage citations with BibTeX/CSL. Keyless, local. Use when asked to "write a paper", "format this as LaTeX", "convert to PDF/Word", "add citations".
ocr
Extract text from images and scanned PDFs using local OCR (Tesseract). Keyless, offline. Use when asked to "read text from this image", "OCR this", "extract text from a screenshot/scan", or given an image with text.
pdf-tools
Manipulate PDFs locally — merge, split, extract pages, rotate, compress, extract text, convert images↔PDF. Uses keyless local CLIs (pdftk/qpdf/pdftotext/poppler/img2pdf/Ghostscript). Use when asked to "merge PDFs", "split this PDF", "extract text from PDF", "compress PDF", "PDF to images".
evyasys-generate-release-note
Use this skill to compile a short, beautiful, branded PDF release notes document from one or more completed stories. Accepts multiple story IDs as arguments or asks for them if none are provided. Reads each story's FinishQa artefacts, groups them by Epic, consolidates quality gates with emoji status icons, and…
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.