Prismer Cloud is an infrastructure layer for AI agents that provides shared learning, compressed context, persistent memory, collaboration, messaging, tasks, identity, and workspaces. It is for agents and the people building or using long-running agent systems that need information and outcomes to persist across sessions. The catalogue entries provide skills, hooks, agents, instructions, and a plugin for using Prismer Cloud.
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 Prismer-AI/PrismerCloud --skill ingestgit clone --depth 1 https://github.com/Prismer-AI/PrismerCloudWrote 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/prismer-ai/prismercloud/ingest)<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/ingest"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/ingest/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/prismer-ai/prismercloud/ingest"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/ingest.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 | $0.00132 | $0.01319 |
| Opus 5.5 | $0.00053 | $0.00528 |
| Sonnet 5.5 | $0.00026 | $0.00264 |
| Haiku 4.5 | $0.00013 | $0.00132 |
Grade A, and why
ingest scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
All of them use the same workspace-billed cloud lane (`/api/context/load`). Never script HTTP via `execute_code`/subprocess/curl for web research. How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest
Use this skill to bring external web content into your context by navigating, not by dumping whole pages: the first call returns each document's outline with refs, later calls read only the sections you choose, as original text.
Local documents (PDF text extraction + OCR) are handled by the
liteparseskill, not here — it's a local-first, zero-network tool with Tesseract + PDFium bundled.ingestcovers web URLs only.
When to use
- The user pastes a URL or asks "what does this page say".
- The user asks to research a topic ("AI agent frameworks 2025") — search, then read the relevant sections of the top pages.
- A task description contains URLs that need to be resolved into actual content before the assignee can act.
Attached PDFs / images / scans → use the
liteparseskill (local-first PDF text + OCR), notingest.
Tools
| Runtime | Discover (query or URL) | Read sections |
|---|---|---|
| Hermes | workspace_web_search(query, limit) or web_load(input="<URL>") |
web_load(input=["<ref>", "<ref>"]) — up to 5 refs per call |
| Other runtimes | cloud search "<query>" / cloud load <url> |
cloud load '<ref>' '<ref>' — quote refs in the shell |
All of them use the same workspace-billed cloud lane (/api/context/load). Never script HTTP via execute_code/subprocess/curl for web research.
How navigation works
- Discovery searches (default top 5, max 10) or fetches the URL, caches the full text, and returns per document
status: "ok",url,title,refand anoutlineof{title, ref, hasChildren, estimatedTokens}. - An outline is not evidence. Titles only tell you where to look; only
contentis the source's text. - Reading a ref: a section with children returns its sub-outline; a leaf returns
content— the original extracted text (not a summary) withsource.urland its character range. UsecontentRefto read a whole section as text instead of its sub-outline. nextRefmeans the outline or text continues. Follow it only when you still need more of that section.next_callsare mechanical suggestions (continuations, or each document's first section), not a relevance ranking — choose sections from the outline titles and your question.status: "deferred"(BUDGET_EXHAUSTED): the response budget ran out before that item; call again with itsref.status: "error":FETCH_FAILED/CONTENT_UNAVAILABLE— the page could not be read;REF_UNAVAILABLE— the ref expired (7 days) or is not yours, so load the URL again for a fresh one.- Copy refs exactly as returned. Never build or edit a ref (including its
offset).
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 · +46 tokens per session a6c9b3873519
- 24d ago Changed · -32 lines · +7 tokens per session e613d5e11be6
- 1mo ago First seen · 106 lines · 79 tokens per session scan A 17bfe67faa32
ingest is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,363 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 1,319 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
markitdown
A Python utility for converting various file formats (PDF, Word, Excel, PowerPoint, etc.) to Markdown. Use this skill to install and use MarkItDown for document conversion.
markitdown
Convert files, URLs, and documents to Markdown using the markitdown MCP server. Activate when the user asks to convert, extract, or read content from PDFs, Word docs, PowerPoints, spreadsheets, images, audio files, or any URL.
Read, extract, merge, split, rotate, watermark, create, fill, encrypt, decrypt, and OCR PDF files. Use when the user mentions PDFs or needs any document workflow centered on .pdf files.
markitdown
Convert files and office documents to Markdown, including PDFs, Office files, images with OCR, audio with transcription, HTML, archives, and structured data. Use when the user needs markdown extraction or document-to-markdown conversion.
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.