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 agentlas-ai/agentlas-desktop --skill documentgit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/document)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/document"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/document/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/agentlas-ai/agentlas-desktop/document"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/document.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 | $0.00026 | $0.00872 |
| Opus 5.5 | $0.00010 | $0.00349 |
| Sonnet 5.5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
document 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 2d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steps
harness_call {"operation":"document.list"}: reuse a session already open in this conversation. Otherwise callharness_call {"operation":"document.open","args":{"path":"<absolute path>"}}. For a new file, calldocument.createwith a path that does not exist yet (.docx, or.hwpxfor Hangul).- Read the returned
outline. The first line gives the paper and body size (# page 210x297mm, body 11pt). Each line starts with the id that ops address:[b3]is a paragraph, andb5.r2c1is a table cell (row 2, column 1).{bold 14pt center}shows the current format. For a fresh outline, usedocument.readwithsessionId. - Edit with
harness_call {"operation":"document.apply","args":{"sessionId":"…","ops":[…]}}. Send a few ops per call so the owner can follow along. - When the work is done, or when the owner asks, save with
harness_call {"operation":"document.save","args":{"sessionId":"…"}}. - To check the layout, call
harness_call {"operation":"document.render","args":{"sessionId":"…"}}. It returns up to 4 pages as images, as the document is now (saved or not), and lists the blocks that run off the page. When the reply hasnext, call again with itsfromuntil every page has been seen.
Ops
{"op":"set_text","target":"b3","text":"…"}replaces a paragraph or table-cell text.\nis a line break inside it.{"op":"insert_text","target":"b3","text":"…","at":0}inserts text. Withoutat, the text is appended.{"op":"insert_paragraph","after":"b3","text":"…","heading":2}adds a paragraph."after":"start"puts it first.headingis optional;"pageBreak":truestarts a new page (docx, hwpx).{"op":"insert_table","after":"b3","rows":[["구분","내용"],["성명",""]],"widths":[1,3]}: docx and hwpx.widthsgives column ratios."merges":[{"cell":"r2c2","colSpan":3}]merges cells. In an outline,~marks a cell covered by the merge to its left or above.{"op":"delete_block","target":"b3"}{"op":"set_format","target":"b3","format":{"bold":true,"size":14,"color":"#c00000","align":"center"},"heading":1}sets the format of a whole paragraph or cell.nullremoves a value;heading0 is body text.{"op":"set_format","target":"b5.r1c1","format":{"fill":"#d9e2f3","bold":true}}shades a table cell (a header row, a label column).
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.
- 2d ago Changed ab7253da02c8
- 3d ago Changed · +1 lines ebf1fd0526b5
- 4d ago First seen · 37 lines · 26 tokens per session scan A 19165c530d85
document is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 872 once invoked, about $0.0001 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 2026-10-18.
Other skills, from other repositories
cua-volume
Use Cua Volume, the one volume every Space and agent of this user shares. Inside a Space it is mounted as a folder (/volume on Linux, /Cua Volume on macOS), so any program reads and writes it directly. Use it for anything that must outlive this Space - your memory and outputs in your agent home, shared reference in…
doc-ingest
Extract readable text from document files — PDF, XLSX/CSV/TSV, DOCX, PPTX, and plain-text formats — so any task that arrives with an attachment can actually consume it.
md2pdf
Convert a Markdown file to PDF with GitHub-style formatting using the md2pdf tool.
delive-transcript-analyzer
Analyze, summarize, and extract insights from DeLive transcription sessions. Use when: user mentions DeLive, transcription, meeting transcripts, live captions, audio transcription, AI correction, corrected transcript, or transcript analysis; user wants to search, retrieve, summarize, correct, or process recorded…
hermesoffice-documents
Produce and edit Word documents in HermesOffice Docs — block editing, tracked changes, reports, and the templates/docs library (meeting notes, business plan, PRD, decision memo, and more). Load for any request that creates or restructures a document.
electron-expert
Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.