analyze-kb

analyze-kb is a command for Claude Code from Abilityai/cornelius. It costs 12 tokens per session (514 once invoked), scanned A, original, MIT.

A command for examining the structure and connections in an Obsidian knowledge base, which is a folder of linked notes.

In plain words
What is it for?
Use it to gather vault statistics, inspect note directories and major hubs, map connections, and update a knowledge-base analysis report.
Why use it?
It condenses the vault's organization and important thematic relationships into an easier-to-manage report.

Command for Claude Code

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 commands/abilityai/cornelius/analyze-kb
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

Made for: Claude Code.

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 analyze-kb

README.md
[![agentmods](https://agentmods.dev/badge/commands/abilityai/cornelius/analyze-kb.svg)](https://agentmods.dev/commands/abilityai/cornelius/analyze-kb)
Your own site
<a href="https://agentmods.dev/commands/abilityai/cornelius/analyze-kb"><img src="https://agentmods.dev/badge/commands/abilityai/cornelius/analyze-kb.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00012 $0.00514
Opus 5 $0.00006 $0.00257
Sonnet 5 $0.00002 $0.00103
Haiku 4.5 $0.00001 $0.00051

Measured 4d ago against content hash e647fc10250a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-kb 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/analyze-kb.md · 42 lines

What it actually says

Analyze the Obsidian knowledge base structure and regenerate a condensed, manageable analysis report.

Follow these steps:

  1. Get vault statistics using mcp__smart-connections__get_stats
  2. List all notes with full directory tree using Bash find:
    find /path/to/your/vault -name "*.md" -type f | head -50
    
  3. Use Glob to explore directory structure:
    • All notes: Brain/**/*.md
    • Permanent notes: Brain/02-Permanent/*.md
    • MOCs: Brain/03-MOCs/*.md
    • Sources: Brain/01-Sources/**/*.md
  4. Read key hub notes from major clusters using Read tool (Dopamine, Self/Buddhism, Decision-Making, Flow, etc.)
  5. Use mcp__smart-connections__get_similar_notes to identify highly connected notes
  6. Use mcp__smart-connections__get_connection_graph to map relationship networks
  7. Analyze thematic clusters, hierarchical organization, and conceptual architecture
  8. Use Edit or Write to update the knowledge-base-analysis.md file with a condensed report (target: ~600-800 lines max):
    • Executive summary with key statistics
    • Hierarchical structure mapping (condensed)
    • 6 major thematic hubs with hub nodes (core thesis + key notes only)
    • Network properties and connectivity (metrics + critical bridges)
    • Content topology and source analysis (top-tier influences only)
    • Intellectual trajectory and maturity assessment (phases + current focus)
    • Recommendations for enhancement (high priority only)

CRITICAL OUTPUT REQUIREMENTS:

  • Length target: 600-800 lines maximum (50% of previous verbose reports)
  • Prioritize: Core insights, actionable frameworks, critical statistics, key bridge notes
  • Eliminate: Excessive examples, redundant explanations, verbose elaborations
  • Focus: What's unique, what's actionable, what's growing, what's next
  • Style: Bullet points over paragraphs, tables over lists where appropriate
  • No duplication: Say things once, clearly, then move on

Generate a condensed, scannable, high-signal report that reveals the knowledge base's personality, cognitive fingerprint, and growth opportunities without overwhelming detail.

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. 4d ago First seen · 42 lines · 12 tokens per session scan A e647fc10250a

Subscribe to this mod's changes

analyze-kb is a command published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 12 tokens to every session and 514 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.