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 gabors-data-analysis/da-w-ai --skill read-pdfgit clone --depth 1 https://github.com/gabors-data-analysis/da-w-aiWrote 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/gabors-data-analysis/da-w-ai/read-pdf)<a href="https://agentmods.dev/skills/gabors-data-analysis/da-w-ai/read-pdf"><img src="https://agentmods.dev/badge/skills/gabors-data-analysis/da-w-ai/read-pdf/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/gabors-data-analysis/da-w-ai/read-pdf"><img src="https://agentmods.dev/badge/skills/gabors-data-analysis/da-w-ai/read-pdf.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 | $0.00060 | $0.00444 |
| Opus 5.5 | $0.00024 | $0.00178 |
| Sonnet 5.5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
read-pdf 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 6d 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
Read a PDF: text first
Reading a PDF directly is unreliable: long files get cut, columns get mixed up, and the agent may answer from a partial view without saying so. So we always extract the text first, save it, and work from the saved text.
Steps
- Extract the text. Use the Python package
pymupdfin this project's environment (install it with the project's package manager if missing). Save the text next to the PDF with the same name and a.txtending, for examplepaper.pdf->paper.txt. Mark each page with a line like=== page 7 ===so page numbers can be cited. - Check the extraction. Report the number of pages and the number of characters. If a page has almost no text (under ~200 characters), it is probably a scanned image. For those pages, render them to PNG (150 dpi is enough) and read the images. Tell the user which pages were read as images.
- Work from the
.txtfile, not the PDF. For long documents (more than ~40 pages), read it section by section rather than all at once. - Cite page numbers for every claim, number or quote taken from the document. Quote exactly; never paraphrase inside quotation marks.
- Tables: when the user needs a table, copy it into a CSV in
data/raw/and then check three numbers from the CSV against the page image.
What to tell the user at the end
- what was extracted (pages, characters, any pages read as images)
- where the
.txtfile is - anything that could not be read well (garbled tables, formulas, footnotes)
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.
- 6d ago First seen · 34 lines · 60 tokens per session scan A 514d39c0c11b
read-pdf is a skill published in the GitHub repository gabors-data-analysis/da-w-ai (22 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 444 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
read-pdf compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| read-pdfgabors-data-analysis/da-w-ai | Skill | 22 | yesterday | MIT | A | 60 | Claude Code, Codex |
| pptx-importTHU-MAIC/OpenMAIC | Skill | 43k | yesterday | MIT | A | 125 | Claude Code, Codex |
| pdf-analysisOpenSenseNova/SenseNova-Skills | Skill | 6.1k | yesterday | MIT | A | 48 | Claude Code, Codex |
| sn-da-non-spreadsheet-analysisOpenSenseNova/SenseNova-Skills | Skill | 6.1k | yesterday | MIT | A | 234 | Claude Code, Codex |
| annotate-paper54yyyu/zotero-mcp | Skill | 5.9k | 2d ago | MIT | A | 82 | Claude Code, Codex |
| dedao-dlyann0917/dedao-dl | Skill | 920 | yesterday | MIT | A | 134 | Claude Code, Codex |
| explorable-beamerclaesbackman/AI-research-feedback | Skill | 560 | 16d ago | MIT | A | 206 | Claude Code, Codex |