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 BlackBeltTechnology/pi-agent-dashboard --skill document-convertergit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/document-converter)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/document-converter"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/document-converter/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/blackbelttechnology/pi-agent-dashboard/document-converter"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/document-converter.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 | $0.00097 | $0.00997 |
| Opus 5 | $0.00048 | $0.00498 |
| Sonnet 5 | $0.00019 | $0.00199 |
| Haiku 4.5 | $0.00010 | $0.00100 |
Grade A, and why
document-converter 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Converter
TypeScript facade (@blackbelt-technology/pi-dashboard-document-converter) over
the Dockerized pi-doc-engine Python engine. Always call the facade — never
Python, docling, pandoc, or the nano-banana CLI directly. The engine is
quarantined in Docker; the facade is the only call surface.
Internals reference: packages/document-converter/README.md (facade API),
packages/document-converter/engine/README.md (JSON docker run contract).
Do NOT read the vendored Python under engine/document_converter/.
Prerequisites
- Docker available; image built:
cd packages/document-converter && npm run build:image. Thepi.toolsmanifest (package root) declarespi-doc-engineas adocker-imageprobe —pi-dashboard-ensure <package-root>/package.jsonreports image presence and the first-party build hint (confirm-gated) via the registry's Settings → Tools row. - Styled diagrams (nano-banana) need
GEMINI_API_KEYat run time; absent or on failure, rendering falls back to mmdc (never hard-fails).
Two directions
Ingest — any format → Markdown for kb
import { createDocumentConverter } from "@blackbelt-technology/pi-dashboard-document-converter";
const dc = createDocumentConverter({ image: "pi-doc-engine:0.1.0", stagingDir: "/abs/kb-staging" });
await dc.convertToMarkdown("/docs/report.pdf"); // digital PDF (auto: native-first)
await dc.convertToMarkdown("/docs/scan.pdf", { // scanned HU PDF
ocr: { mode: "force", lang: ["hungarian", "english"], engine: "tesseract" },
});
await dc.convertToMarkdown("/docs/huge.pdf", { tables: "off" }); // escape hatch: skip TableFormer
Output .md lands in stagingDir with provenance frontmatter. Feed kb via its
existing filesystem source (kb is NOT modified):
kb index --source /abs/kb-staging
kb search "<query>" --source /abs/kb-staging
OCR lang takes canonical names ("hungarian"); the facade maps to per-engine
codes. A wrong name raises OCR_LANG_UNSUPPORTED — no silent empty OCR. Default
mode: auto skips OCR on digital PDFs.
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 Changed · +4 lines ba7cb00bb996
- 9d ago First seen · 80 lines · 97 tokens per session scan A aca385fcca44
document-converter is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (278 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 997 once invoked, about $0.0005 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
pdf-processor
Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
document-processor
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.
akihtmlreport
Visualize a complex report that already exists in the conversation as one self-contained HTML file — nothing else, no new analysis. Distills a dense analysis/report already discussed into a single-file, ultra-wide, visually dense HTML report (REPORT.html) at the project root, for content too dense to stay legible as…
OCR and Documents
Recover text from scanned or image-heavy documents before attempting structured analysis or downstream writing tasks.
Nano PDF
Extract, inspect, and summarize PDFs quickly with lightweight tooling before escalating to heavier OCR or layout workflows.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.