Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
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 Orkas-AI/Orkas --skill 36bd44ae956cgit clone --depth 1 https://github.com/Orkas-AI/OrkasWrote 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/orkas-ai/orkas/36bd44ae956c)<a href="https://agentmods.dev/skills/orkas-ai/orkas/36bd44ae956c"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/36bd44ae956c/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/orkas-ai/orkas/36bd44ae956c"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/36bd44ae956c.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 | $0.00003 | $0.00629 |
| Opus 5.5 | $0.00001 | $0.00252 |
| Sonnet 5.5 | $0.00001 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
pdf-editing 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 1mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Editing
Tool Route
Use the bundled tools; do not install nano-pdf, pypdf, qpdf, Poppler, or another PDF package during a task.
- Call
read_fileswith onepathsitem for a normal PDF; extraction is prepared in the same call. - For scanned or image-only pages, call
pdf_renderonly on needed pages and read the returned images with the current model. If it cannot read images, ask for readable text or a vision-capable model; do not install a recognition engine. Mark unreadable fields instead of guessing. - Use
create_pdfwithsource_type:"markdown"for a text-first new PDF orsource_type:"html"for tables and custom layout. - Use
edit_pdffor deterministic edits to an existing PDF: merge, extract, delete, reorder, rotate, watermark, visible text/image overlay, and form filling. - Use
pdf_renderon every changed page and representative unchanged pages before delivery. - Every
edit_pdfoutput is a new path. Read that new output withread_files; its first call prepares extraction before returning content.
Editing Rules
- Work from the user's source but always write
edit_pdfoutput to a separate.pdf; never overwrite the only source. - Page numbers passed to
edit_pdfandpdf_renderare 1-based. Inspect page count/content before destructive page operations. - Use
extract_pagesto split or select pages. Usemergewithinput_pathsin the exact desired order. - Treat
overlay_textas visible annotation/replacement artwork only. It does not remove underlying text and is not secure redaction. - Arbitrary replacement of existing PDF text is not structurally reliable. Prefer editing the source DOCX/XLSX/PPTX and regenerating the PDF; otherwise use a disclosed visual overlay and inspect it.
- Do not claim legal-grade redaction, digital signing, encryption, or password removal: these are not part of the current built-in contract.
- For forms, use exact field names. Render the result and confirm values, checkboxes, and flattening behavior in a PDF viewer when fidelity matters.
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.
- 1mo ago Changed fc6d3d9793d0
- 1mo ago First seen · 39 lines · 3 tokens per session scan A 7aea37c6917d
pdf-editing is a skill published in the GitHub repository Orkas-AI/Orkas (2,179 stars, last pushed today), licensed MIT. It adds 3 tokens to every session and 629 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
Read, extract, split, merge, rotate, watermark, fill, OCR, or create PDF files with verification of page counts and text extraction.
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.
sn-da-non-spreadsheet-analysis
A skill for extracting and analysing content from Word files, PDFs, and PowerPoint presentations. It can work with text, tables, numbers, charts, formatting, and information across multiple documents.
pptx-posters
Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual…
report-generator
A report-generation tool for producing SEO and GEO analysis reports in formats such as Markdown, HTML, PDF, JSON, and Excel. It also supports charts, templates, data processing, and interactive report elements.
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.