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 Cloudgeni-ai/opengeni --skill documentsgit clone --depth 1 https://github.com/Cloudgeni-ai/opengeniWrote 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/cloudgeni-ai/opengeni/documents)<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/documents"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/documents/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/cloudgeni-ai/opengeni/documents"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/documents.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 | $0.00094 | $0.01600 |
| Opus 5.5 | $0.00038 | $0.00640 |
| Sonnet 5.5 | $0.00019 | $0.00320 |
| Haiku 4.5 | $0.00009 | $0.00160 |
Grade A, and why
documents 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documents
The durable artifact is the default working document. It is the same live object the user sees in the Artifacts dock and full editor. Never create a mutable DOCX shadow, publish a sandbox file, or alternate between file and artifact state. The exception is a file the user sends to be changed, or a requested file format the artifact cannot export; see "Requested Word or PDF files" below.
Create a document when the user asks for a document, asks to edit an existing document artifact, or when a deliverable is too long to read comfortably in chat (several pages); otherwise answer in chat, including briefs, letters, plans and reports written on request. This also applies when a report is a secondary output of another task, such as a Knowledge cleanup audit. If the session has a goal, declare the report through the goal tools before authoring: append the report requirement without replacing the standing objective. Do not create a goal only to declare a document. After authoring, reply with a short summary and the artifact link, not a restatement of the document. Ordinary chat answers, brief progress updates, internal worker findings, code navigation and explicitly requested local-file work are not report deliverables.
Read references/api.md before editing a document artifact; a
sent or requested file (below) does not need it.
When using skill_read, request that relative path from this Skill; reading
does not materialize a local folder. Use an existing local copy only when the
Skill was installed or explicitly checked out to the filesystem.
Choose the canonical object
- If the user means “this document” or a visible document, call
opengeni__editable_artifact_list, thenopengeni__editable_artifact_getwhen needed. Do not guess an id from chat. - To begin empty, call
opengeni__editable_artifact_createwith modalitydocument. - To begin from a ready workspace DOCX, call
opengeni__editable_artifact_importwith itsfileId. The source file remains immutable provenance; the returned artifact becomes the working object. - Use a standalone local DOCX only when the user explicitly asks to manipulate
sandbox-local bytes and the pinned local runtime is actually available.
Normal import/export uses workspace
fileIdboundaries without local bytes.
What ships with it
2 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.
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 · +22 lines · +1 tokens per session 4fe19866be2c
- yesterday First seen · 101 lines · 93 tokens per session scan A 901569c7c96f
documents is a skill published in the GitHub repository Cloudgeni-ai/opengeni (205 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 1,600 once invoked, about $0.0004 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 2026-10-21.
Other skills, from other repositories
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
output-build-workflow
Implement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an existing plan, or after output-plan-workflow has produced a plan and the user is ready to build.
output-workflow-trace-file
Read and render the output of a local Output SDK workflow trace file as clean readable markdown. Use when the user wants to view what a recent workflow produced, see the result from a local trace file, or render trace output as a document.
documents
Create, read, edit, and verify PDFs, scanned documents, PowerPoint, Word, and spreadsheet files.
cite-sources
How to attribute every factual claim to a corpus document.
extracto-cli
Use when the user wants to extract text from PDFs or images, manage OCR jobs, or work with output presets via the local Extracto OCR webapp. Talks HTTP to a running Extracto instance using the bundled extracto CLI.