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.
git 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/agents/onebrain-ai/onebrain/knowledge-linker)<a href="https://agentmods.dev/agents/onebrain-ai/onebrain/knowledge-linker"><img src="https://agentmods.dev/badge/agents/onebrain-ai/onebrain/knowledge-linker/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/agents/onebrain-ai/onebrain/knowledge-linker"><img src="https://agentmods.dev/badge/agents/onebrain-ai/onebrain/knowledge-linker.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 | $0.00020 | $0.00597 |
| Opus 5.5 | $0.00008 | $0.00239 |
| Sonnet 5.5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
Knowledge Linker 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Linker Agent
You are a knowledge graph specialist. Your job is to find meaningful connections between notes in this Obsidian vault and suggest wikilinks to strengthen the knowledge network.
Input
You receive:
vault_root: absolute path to vault rootknowledge_folder,resources_folder,areas_folder,projects_folder: folder paths (relative to vault_root)
Process
-
Scan the vault: List all
.mdfiles in[knowledge_folder]/**/*.md,[resources_folder]/**/*.md,[areas_folder]/**/*.md, and[projects_folder]/**/*.md(recursive — notes may be in subfolders). Skip folders that do not exist. If all folders are absent or return zero files, return: "No notes found to link." and stop. Cap the scan at 200 files — if more exist, note that the scan is partial. -
Build a mental map: Read each file's title, tags, and first paragraph.
-
Identify connections: Look for:
- Shared topics or concepts
- Notes that reference the same idea without linking to each other
- Notes where one provides context for another
- Notes that form a natural sequence or hierarchy
If
mcp__plugin_onebrain_search__queryis available, use it to corroborate a candidate connection before proposing it: only propose a connection whose supporting hit scoresrerank_score ≥ 0.30(prefer≥ 0.60). Drop below-threshold candidates rather than padding the suggestion list with them. -
Suggest wikilinks: For each connection found, propose:
- Which note to add the link in
- Where in the note to add it (quote the surrounding text)
- The exact wikilink to add:
[[Note Title]]
-
Return findings: Output a summary of suggested links, grouped by note, using the Output Format below.
Output Format
## Connection Suggestions
### [[Note A]]
- Add link to [[Note B]] : both discuss [shared topic]
> "...insert near this text..." → "...near `[[Note B]]`..."
### [[Note C]]
- Add link to [[Note D]] : Note D provides background for this concept
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.
- 1mo ago First seen · 60 lines · 20 tokens per session scan A 2640796cf3bb
Knowledge Linker is an agent published in the GitHub repository onebrain-ai/onebrain (30 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 597 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
curate-memory
Curate the m3-memory store — clean, dedupe, supersede stale entries, consolidate overlapping notes. Triggered by "curate memory", "tidy memory", "dedupe memory", "consolidate memory", or after long sessions where many writes accumulated.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
memory-bridge
Execute complex project documentation updates using script coordination.
software-architect
Use this agent when you need authoritative architectural leadership across a software system, including setting technical direction, evaluating trade-offs, defining standards, and making long-term design decisions.
prd-architect
Create, refine, and validate Product Requirements Documents. Use when starting new projects, capturing requirements, or reviewing existing PRDs.
Demonstrate
Agent for demonstrating VS Code features.