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 dieter-medium/bidi2pdf --skill pdf-recipegit clone --depth 1 https://github.com/dieter-medium/bidi2pdfWrote 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/dieter-medium/bidi2pdf/pdf-recipe)<a href="https://agentmods.dev/skills/dieter-medium/bidi2pdf/pdf-recipe"><img src="https://agentmods.dev/badge/skills/dieter-medium/bidi2pdf/pdf-recipe/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/dieter-medium/bidi2pdf/pdf-recipe"><img src="https://agentmods.dev/badge/skills/dieter-medium/bidi2pdf/pdf-recipe.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 | $0.00077 | $0.01070 |
| Opus 5.5 | $0.00031 | $0.00428 |
| Sonnet 5.5 | $0.00015 | $0.00214 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade A, and why
pdf-recipe 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 today.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write and run a bidi2pdf recipe
A recipe is a rendering contract: the steps a page needs before it is printed, and what the PDF must
be like afterwards. It is not a general automation script. The source of truth for its shape is
bidi2pdf schema recipe; read it once before writing one.
Does not: log in through forms, follow links across pages, or extract data. One page, prepared
and printed. For a plain page without steps, render is enough (the render-pdf skill).
Ground rules
- bidi2pdf is the renderer. If it fails, report its
error.code,error.hintand exit code; never make the PDF or screenshot another way (Chrome's own print-to-PDF, another PDF engine). - Install nothing unasked. Name what is missing and suggest a way (the
render-pdfskill's preflight); run nothing that changes the system without the user's yes. - bidi2pdf's results first. Read its
--jsonresult instead of inspecting the PDF with other tools.
1. Write it
version: 1
source:
url: https://example.com/invoice/123
actions:
- wait_for:
selector: "#invoice"
timeout: 10
- click:
selector: "#show-details"
- wait_network_idle:
timeout: 10
assert:
- selector_exists:
selector: "#total"
- no_console_errors: true
- page_count: 2
- pdf_text_present:
text: "Invoice #123"
output:
pdf: invoice.pdf
manifest: invoice.manifest.json
- source: exactly one of
url,file,stdin. - actions run in order, after the page has loaded:
wait_fortakes exactly one ofselector,paged_js: true(a Paged.js page exists) orscript(a JS expression that becomes truthy), plus an optionaltimeout(default 10 s).click,evaluate(a script, optionallyassign:its result),inject_script/inject_style(content:orurl:).set_viewport(width,height, optionaldevice_pixel_ratio).wait_network_idle(timeout).emulate_media(media: screen|print,color_scheme: light|dark,reduced_motion) - from the 0.1.23 or later.
- assert runs after printing. Page checks:
selector_exists,text_present,no_console_errors,no_network_failures,fonts_loaded. PDF checks:page_count,pdf_text_present,pdf_not_blank- these need thepdf-readergem. - output needs at least one of
pdf,manifest,screenshot.
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.
- today Changed · +9 lines c8257cf48b06
- yesterday First seen · 84 lines · 77 tokens per session scan A 00b17c4e996d
pdf-recipe is a skill published in the GitHub repository dieter-medium/bidi2pdf (58 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,070 once invoked, about $0.0003 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 2026-10-26.
Other skills, from other repositories
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
km-content-extraction
Content extraction routing for KM - local documents (HWP/HWPX/PDF/DOCX/XLSX), web, and vault sources. Use when input is a local file or when km-workflow reaches Phase 2 with a non-URL input.
svg-press
Teaches agents how to hand-craft self-contained SVG diagrams that render correctly in browsers, tags, and Playwright PDF/PNG. Covers containment math, viewBox sizing, arrow construction, text hierarchy, KDCube brand color tokens, semantic zone fills, badges, the PNG inspection loop, writepng parameters, multi-diagram…
fullbleed
Use Fullbleed PDF Engine to create or modify document-generation projects for PDFs, reports, invoices, statements, forms, certificates, letters, accessible PDF/PDF-UA, archival PDF/PDF-A, print-ready PDF/PDF-X, transactional output, and fixed or reflowing variable-data/VDP jobs from structured content using Python and…
thumbnail-of-pptx
Capture a thumbnail image of a slide from a OneDrive/Office presentation link. Opens the PowerPoint web viewer in a headless browser and screenshots the slide canvas, producing a clean 16:9 image with no viewer chrome. Works even when the PPTX is not downloadable (e.g. personal OneDrive shares), since it screenshots…
export-presentation
Export HTML slide presentations to PDF or PNG screenshots.