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 evoelsewhere/evoflux --skill pdf-officialgit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/pdf-official)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/pdf-official"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/pdf-official/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/evoelsewhere/evoflux/pdf-official"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/pdf-official.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.02387 |
| Opus 5 | $0.00057 | $0.01193 |
| Sonnet 5 | $0.00023 | $0.00477 |
| Haiku 4.5 | $0.00012 | $0.00239 |
Grade A, and why
pdf-official 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF skill
An Apache-2.0 toolkit for reading, composing, transforming, and filling PDF files. Written from scratch on top of permissively-licensed open-source libraries (pypdf, pdfplumber, pypdfium2, reportlab, pdf-lib, qpdf) so this can be embedded in commercial projects without special agreement.
Route the task
Pick the sub-guide by the verb of the request.
| Task | Path | Read |
|---|---|---|
| Pull text / tables / metadata / images out of an existing PDF | Extract | extract.md |
| Combine, carve, rotate, crop, watermark, encrypt, or shrink | Transform | transform.md |
| Build a PDF that doesn't exist yet (report, invoice, certificate) | Compose | compose.md |
| Fill a form (AcroForm or scanned) | Interactive | interactive.md |
| Scanned / image-only PDF (no selectable text) | Extract → OCR | extract.md §5 |
If a task mixes several of these, follow the order: probe → plan → extract or compose → validate.
Every path starts with a probe. scripts/survey.py returns page count,
whether the file is encrypted, whether it has an AcroForm, and whether
page 1 looks like a scan.
Pipeline
Probe first, always. Composition passes two gates; extraction and transformation pass none.
Phase 0 Probe the file ← page count, encryption, form, text layer
Phase 1 Settle the brief ← composition only, ask once
Phase 2 Page model ← GATE: composition only
Phase 3 Extract / transform / compose
Phase 4 Verify and repair ← loop until it passes
Phase 5 Hand off
Phase 0 — Probe. scripts/survey.py answers more than any question would.
It decides which path applies and stops you from asking the user what the file
already states.
Phase 1 — Settle the brief. Only for composition, and only for what the
request leaves open: reader and use, content boundaries, fidelity constraints.
One ask_user call, at most three questions. Two questions are never
defaultable — an encrypted file needs its password from the user, and a change
that would break a signature or pass off cropping as redaction needs their
decision first. Read interview.md.
What ships with it
20 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.
- agents/evoflux.yaml 262 B
- compose.md 12 KB
- evals/trigger-cases.json 955 B
- extract.md 6.2 KB
- interactive.md 9.8 KB
- interview.md 3.1 KB
- LICENSE 2.3 KB
- README.md 4.4 KB
- scripts/apply_values.py 6.7 KB runs code
- scripts/carve.py 3.9 KB runs code
- scripts/combine.py 2.4 KB runs code
- scripts/overlay_text.py 11 KB runs code
- scripts/probe_fields.py 12 KB runs code
- scripts/recognize.py 3.9 KB runs code
- scripts/render_pages.py 3.6 KB runs code
- scripts/reorient.py 2.5 KB runs code
- scripts/sanity_check.py 3.7 KB runs code
- scripts/survey.py 2.8 KB runs code
- scripts/text_dump.py 5.7 KB runs code
- transform.md 6.8 KB
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 · 177 lines · 115 tokens per session scan A 71f5613e8eaf
pdf-official is a skill published in the GitHub repository evoelsewhere/evoflux (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 115 tokens to every session and 2,387 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 2026-09-06.
Other skills, from other repositories
Read, create, inspect, render, and verify PDF files where visual layout matters, including fillable AcroForms. Use Poppler rendering plus Python tools such as reportlab, pdfplumber, and pypdf for generation and extraction.
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…
pdf-monster
Analyze PDF files by converting them into agent-readable text, OCR text, page render images, and extracted embedded images without polluting the working directory. Use when an agent needs to read, summarize, inspect, compare, quote, or reason about PDFs, especially when the foundation model cannot ingest PDFs directly…
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.
Read, extract, split, merge, rotate, watermark, fill, OCR, or create PDF files with verification of page counts and text extraction.
pandoc
Convert documents between formats (Markdown, DOCX, HTML, PDF, RST, EPUB, LaTeX) via the pandoc CLI. Use to transform a document from one format to another.