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/connectnpx skills add onebrain-ai/onebrain --skill connectgit clone --depth 1 https://github.com/onebrain-ai/onebrainWrote 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/onebrain-ai/onebrain/connect)<a href="https://agentmods.dev/skills/onebrain-ai/onebrain/connect"><img src="https://agentmods.dev/badge/skills/onebrain-ai/onebrain/connect.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.01711 |
| Opus 5 | $0.00038 | $0.00856 |
| Sonnet 5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
Grade A, and why
connect 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 4d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect
Find meaningful connections between your notes and suggest wikilinks to build a richer knowledge graph.
Step 1: Scope
Ask (or infer from context):
AskUserQuestion:
- question: "What scope do you want to search for connections?"
- header: "Connect Scope"
- multiSelect: false
- options:
- label: "specific note", description: "Find connections for a specific note (you'll name it)"
- label: "entire knowledge base", description: "Scan all projects, areas, knowledge, and resources"
- label: "recently added", description: "Notes added in the last 7 days"
Step 2: Scan Notes
Use the search tools if available for semantic search across notes; fallback: Glob [projects_folder]/**/*.md, [areas_folder]/**/*.md, [knowledge_folder]/**/*.md, [resources_folder]/**/*.md. For search-tool results, only carry forward candidates with rerank_score ≥ 0.30 (prefer ≥ 0.60) into Step 3 — drop anything below 0.30 rather than proposing a weak connection. For each note, extract:
- Title
- Tags (from frontmatter)
- Key concepts mentioned (first 200 words)
- Existing wikilinks already present
If the total note count exceeds 20, delegate to the Knowledge Linker agent instead — see Step 2b.
Step 2b: Delegate to Agent (>20 Notes)
If more than 20 notes are in scope: dispatch the Knowledge Linker agent (agents/knowledge-linker.md) as a foreground sub-agent (run_in_background: false, mode: "bypassPermissions"), passing vault_root, knowledge_folder, resources_folder, areas_folder, and projects_folder. The agent always scans the full vault regardless of the scope chosen in Step 1. Proceed to Step 4 immediately (the agent's output replaces Step 3).
For ≤20 notes: continue with Step 3.
Step 3: Find Connections
Look for:
| Connection Type | Description |
|---|---|
| Conceptual overlap | Both notes discuss the same idea |
| Cause-effect | One note explains why something in another happens |
| Elaboration | One note goes deeper on a concept mentioned in another |
| Contrast | Notes present different perspectives on the same topic |
| Sequence | Notes form a natural progression of ideas |
| Application | One note shows how to apply a concept from another |
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.
- 4d ago First seen · 196 lines · 76 tokens per session scan A 6d8d78faf989
connect is a skill published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 6d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,711 once invoked, about $0.0004 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
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).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
lint-brain
Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".
ingest-article
Ingest an article from a URL or raw text into the brain vault. Extracts key knowledge, determines placement, creates or updates notes, and links to relevant projects. Use when the user shares a URL or text and wants to absorb it into their knowledge base.