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/updatenpx skills add onebrain-ai/onebrain --skill updategit 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 | $0.00069 | $0.04535 |
| Opus 5 | $0.00034 | $0.02268 |
| Sonnet 5 | $0.00014 | $0.00907 |
| Haiku 4.5 | $0.00007 | $0.00453 |
Grade B, and why
update scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Settings merge:** `curl -fsSL https://raw.githubusercontent.com/onebrain-ai/onebrain/{branch}/.claude/settings.json` (see **Fetching raw GitHub content** above — not `WebFetch`, which can return a non-JSON paraphrase Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> **Fetching raw GitHub content (cross-shell).** Every raw fetch in this skill — `plugin.json`, `CHANGELOG.md`, `SKILL.md`, `settings.json` — uses `curl -fsSL <url>` via the Bash tool, **not** `WebFetch`. WebFetch can su How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update
Update OneBrain system files from GitHub to the latest version.
Fetching raw GitHub content (cross-shell). Every raw fetch in this skill —
plugin.json,CHANGELOG.md,SKILL.md,settings.json— usescurl -fsSL <url>via the Bash tool, notWebFetch. WebFetch can summarize or paraphrase content even onraw.githubusercontent.comURLs, silently corrupting JSON parsing and verbatim file writes (see Known Gotchas). Never usegiteither (it hangs on Windows waiting for credentials).
- Bash / zsh / Git Bash / cmd:
curl -fsSL <url>(Windows 10+ ships realcurl.exe). To download straight to a file (e.g. the self-update bootstrap) add-o <dest>.- PowerShell:
curlis an alias forInvoke-WebRequestwith incompatible flags. Read to stdout withInvoke-WebRequest -UseBasicParsing <url> | Select-Object -ExpandProperty Content, or download to a file withInvoke-WebRequest -UseBasicParsing <url> -OutFile <dest>.
Version Check
- Read current version from vault's
plugin.json([agent_folder]/../../.claude-plugin/plugin.jsonor.claude/plugins/onebrain/.claude-plugin/plugin.json) - Read
update_channelfromonebrain.yml(default:stableif field absent). Map to GitHub branch:stable→mainnext→nextN.x(e.g.1.x,2.x) →N.x
- Read new version from repo's
plugin.jsonon the mapped branch withcurl -fsSL(see Fetching raw GitHub content above for the cross-shell form) — neverWebFetch(it can summarize JSON and corrupt the version compare) and nevergit(it hangs on Windows):curl -fsSL https://raw.githubusercontent.com/onebrain-ai/onebrain/{branch}/.claude/plugins/onebrain/.claude-plugin/plugin.jsonwhere{branch}is the mapped branch from step 2. Parse theversionfield from the JSON response. - If equal → say: ✅ Already up to date — v{X.X.X}. and stop
- If newer →
curl -fsSL https://raw.githubusercontent.com/onebrain-ai/onebrain/{branch}/CHANGELOG.md(see Fetching raw GitHub content above); display before proceeding (do not skip or summarize):
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.
- 2d ago First seen · 211 lines · 69 tokens per session scan B b009f5cca379
update is a skill published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 69 tokens to every session and 4,535 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, 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
excalidraw-diagram
Generate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "diagram", "standard excalidraw", "animate".
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
deeppapernote
Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders.