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 agentmods add skills/onebrain-ai/onebrain/importnpx skills add onebrain-ai/onebrain --skill importgit clone --depth 1 https://github.com/onebrain-ai/onebrainWhat 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 | $0.00096 | $0.03201 |
| Opus 5 | $0.00048 | $0.01600 |
| Sonnet 5 | $0.00019 | $0.00640 |
| Haiku 4.5 | $0.00010 | $0.00320 |
Grade A, and why
import 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 3d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import
Process local files into permanent vault notes in [resources_folder]/ (resolved from onebrain.yml; default: 04-resources/).
Usage:
/import: scan default import staging inbox ([inbox_folder]/imports/, resolved from onebrain.yml)/import /path/to/file: import a single explicit file/import --attach: scan inbox and copy supported files into vault for inline Obsidian preview/import /path/to/file --attach: single file with attach
Orchestrator Flow
Step 1: Resolve source and parse flags
Resolve additional folders from onebrain.yml (read the file if it exists at the vault root):
- If
onebrain.ymldoes not exist: use all defaults below. - If
onebrain.ymlexists but cannot be parsed: report the error and stop : do not proceed with unknown folder paths. folders.import_inbox→ default:[inbox_folder]/imports(import staging folder; substituting the resolved[inbox_folder]placeholder)folders.attachments→ default:attachments(for --attach copies)
Use [inbox_folder] and [resources_folder] from session config. Store resolved [attachments_folder] from onebrain.yml above.
Parse arguments:
- Extract
--attachflag if present (remove from path consideration) - If a file path is provided after
/import: this is single-file mode - If no path: this is batch mode (scan inbox)
Single-file mode:
- Validate the file exists. If not, report and stop.
- Determine file type from extension (see Supported File Types below).
- If unsupported type, report:
[filename]is not a supported file type. Supported: PDF, Word, Excel, PowerPoint, images, video, Python/Shell/SQL scripts. Then stop. - Note whether the file is inside the inbox folder (used in cleanup : files outside inbox are never deleted).
- Skip Steps 2 and 3 below. Go directly to Step 4 with this single file.
Batch mode:
- Use
[inbox_folder]resolved in Step 1 above (default:[inbox_folder]/importsfrom onebrain.yml). - List all files recursively in the inbox folder.
- If the inbox folder does not exist, report:
Import inbox not found at
[inbox path]. Run/onboardingto set up your vault, or use/import /path/to/fileto import a specific file. Then stop. - If inbox is empty, report:
🔴 Inbox is empty (
[inbox path]). Add files or use/import /path/to/file. Then stop.
What ships with it
9 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.
- references/excel-handler.md 2.4 KB
- references/image-handler.md 2.5 KB
- references/markitdown-setup.md 1.8 KB
- references/note-template.md 2.6 KB
- references/pdf-handler.md 2.6 KB
- references/pptx-handler.md 1.9 KB
- references/script-handler.md 1.6 KB
- references/video-handler.md 2.4 KB
- references/word-handler.md 2.0 KB
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.
- 3d ago First seen · 270 lines · 96 tokens per session scan A 5fafefceb548
import is a skill published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 96 tokens to every session and 3,201 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
youtube-fetcher
Turn a YouTube video into a structured, Obsidian-ready archival Markdown note containing its transcript, creator metadata, description, chapters, language, and capture provenance. Use when a user shares a YouTube URL or video ID and wants transcripts, captions, subtitles, notes, a knowledge-base record, summarization…
mineru
An AI-Native skill for parsing PDF / Office / image files into clean Markdown with MinerU — a fast, zero-config document parser for AI agents. Works with NO token via the lightweight Agent API and auto-upgrades to the Standard API (token) for large files, batches, and DOCX/HTML/LaTeX export. Use when: (1) Converting…
mineru
An AI-Native skill for parsing PDF / Office / image files into Markdown with MinerU — a fast, zero-config document parser for AI agents. Works with NO token via the Agent API and auto-upgrades to the Standard API (token) for large files, batches, and DOCX/HTML/LaTeX export. Use when converting PDF/Word/PPT/Excel/image…
ingest
Turn messy source notes into structured wiki pages (frontmatter, wikilinks, one folder per type) and update the vault's index, log and hot cache. Use when the user drops files into inbox/ and asks to process them, points at a note or URL to ingest, or pastes raw content to file. Triggers on: "ingest", "ingesta"…
save
File the current conversation's valuable content (analysis, decision, session summary) as a structured wiki note so it isn't lost in chat history. Triggers on: "save this", "guarda esto", "guárdalo en el wiki", "/save", "$save", "file this", "apunta esto", "guarda esta conversación", "save this session".
meeting-processing
Обработка встреч, расшифровок и заметок: извлечение решений, задач, фактов, рисков и устойчивых знаний с маршрутизацией по структуре хранилища. Перед регулярными встречами с историей использует context-compression, чтобы не читать весь архив встреч целиком.