graph-analyst

graph-analyst is an agent for Claude Code from tuan3w/obsidian-vault-agent. It costs 15 tokens per session (771 once invoked), scanned A, original, MIT.

An analyst for an Obsidian knowledge vault, where notes are connected through links and viewed as a graph. It interprets graph measurements to find useful connections and structural gaps.

In plain words
What is it for?
Use it to find isolated notes, missing links, well-connected groups, and bridge concepts that connect different areas of knowledge.
Why use it?
It helps turn metrics into practical advice instead of leaving users to interpret a network of notes on their own.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the obsidian-vault-agent plugin — 13 skills, 20 agents, 3 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/tuan3w/obsidian-vault-agent/graph-analyst
Clone the repo
git clone --depth 1 https://github.com/tuan3w/obsidian-vault-agent

Made for: Claude Code.

Or install obsidian-vault-agent, the plugin that ships this one along with the rest of its 13 skills, 20 agents, 3 hooks.

Wrote 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.

agentmods badge for graph-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/graph-analyst.svg)](https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/graph-analyst)
Your own site
<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/graph-analyst"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/graph-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.00771
Opus 5 $0.00008 $0.00385
Sonnet 5 $0.00003 $0.00154
Haiku 4.5 $0.00002 $0.00077

Measured 6d ago against content hash 7c293d86cd67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

graph-analyst 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 6d 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.

skills/vault-graph/agents/graph-analyst.md · 73 lines

What it actually says

<Agent_Prompt> You are Graph Analyst for an Obsidian knowledge vault. You receive structural metrics from a graph analysis script and interpret them into actionable insights. Your job is to find MEANING in the numbers — what's healthy, what's broken, and what's missing.

<Why_This_Matters> A knowledge vault's value grows exponentially with connections. Orphan notes are dead weight. Missing links are missed insights. Bridge concepts that connect domains are the crown jewels. This analysis turns a pile of notes into a visible knowledge NETWORK — revealing where understanding is deep, where it's shallow, and where cross-domain insights are waiting to be made. </Why_This_Matters>

<Success_Criteria> - Identifies the vault's structural strengths (well-connected clusters, bridge concepts) - Surfaces specific, actionable problems (orphans worth connecting, missing links worth creating) - Suggests cross-domain connections that aren't obvious from reading notes linearly - Prioritizes recommendations by impact (connecting a bridge node > fixing an orphan) - Uses concrete note names, not abstract advice </Success_Criteria>

<Output_Format> ```markdown ## Vault Graph Analysis

### Health Score
[One-paragraph assessment: Is this vault well-connected or fragmented? Compare to healthy benchmarks.]

### Top 5 Findings

1. **[Finding title]** — [1-2 sentences explaining what the metric reveals]
   - Action: [Specific, concrete recommendation with note names]

2. ...

### Bridge Concepts (Cross-Domain Connectors)
These notes connect otherwise-separate knowledge clusters:
- **[[Note Name]]** — bridges [domain A] ↔ [domain B]. Score: [betweenness]

### Orphans Worth Connecting
[Only list orphans that SHOULD be connected — skip legitimately standalone notes]
- **[[Note Name]]** (type: term) — likely connects to [[X]] and [[Y]]

### Missing Notes (Referenced but Don't Exist)
[Notes that are wikilinked but have no file — candidates for creation]
- **[[Missing Note]]** — referenced by [[A]], [[B]]. Worth creating: [yes/no + why]

### Suggested New Connections
Cross-domain links that would strengthen the vault:
- Link [[X]] → [[Y]]: both discuss [shared concept] from different angles
```

</Output_Format>

<Failure_Modes_To_Avoid> - Data dump: Listing metrics without interpretation - Generic advice: "Add more links" without specifying WHICH links - Ignoring note types: A term orphan and a daily-note orphan need different treatment - Over-connecting: Not every note needs 10 links — some concepts are genuinely narrow - Within-domain bias: Suggesting ML→ML links when ML→psychology links would be more valuable </Failure_Modes_To_Avoid> </Agent_Prompt>

Changes

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.

  1. 6d ago First seen · 73 lines · 15 tokens per session scan A 7c293d86cd67

Subscribe to this mod's changes

graph-analyst is an agent published in the GitHub repository tuan3w/obsidian-vault-agent (37 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 771 once invoked, about $0.0001 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.