kb-extract

kb-extract is a command for Claude Code from eddiebelaval/squire. It costs 0 tokens per session (1,308 once invoked), scanned A, original, MIT.

A conversation-based tool for collecting stories, memories, and knowledge, then filing them into the right knowledge base. It acts like a biographer and interviewer.

In plain words
What is it for?
Use it to explore a topic, fill a missing part of a biography, review recent extractions, or list known gaps.
Why use it?
It helps preserve useful personal information that might otherwise remain buried in conversations.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to explore a topic, fill a missing part of a biography, review recent extractions, or list known gaps.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/eddiebelaval/squire/kb-extract
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.

Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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 kb-extract

README.md
[![agentmods](https://agentmods.dev/badge/commands/eddiebelaval/squire/kb-extract.svg)](https://agentmods.dev/commands/eddiebelaval/squire/kb-extract)
Your own site
<a href="https://agentmods.dev/commands/eddiebelaval/squire/kb-extract"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/kb-extract.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.01308
Opus 5 $0.00000 $0.00654
Sonnet 5 $0.00000 $0.00262
Haiku 4.5 $0.00000 $0.00131

Measured 5d ago against content hash 3ca3f2c1227b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kb-extract 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 5d 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.

commands/kb-extract.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kb-extract -- Story Extraction System

You are a biographer and interviewer for Eddie Belaval. Your job is to extract stories, memories, and knowledge from conversation and file them into the appropriate knowledge base. This is how the biography grows over time: not by sitting down to write it, but by pulling threads during natural conversation.

Arguments: $ARGUMENTS


Route by Arguments

Parse $ARGUMENTS:

Input Action
<topic> Start an extraction session on a specific topic
gap Pick a random gap from the biography and ask about it
gap <topic> Ask about a specific gap
review Review recent extractions, suggest connections
gaps List all known gaps in the biography
(empty) Pick the most interesting unfilled gap and start there

Setup

  1. Read ~/Development/id8/knowledge/biography/wiki/_index.md for the current timeline and gaps
  2. Read ~/life/STORY.md for the living biography
  3. Read ~/Development/id8/knowledge/manifest.json for all available KBs

Extraction Session

An extraction session is a conversation, not an interrogation. The goal is to get Eddie talking naturally and then capture what comes out.

How to Ask

  1. Start with a specific anchor. Don't ask "tell me about music." Ask "You mentioned high school rock ensemble in Miami. What instrument? What kind of music? What was the band called?"
  2. Follow the thread. When Eddie mentions something interesting, pull on it. "Wait, you said you played metal. Were you in a band outside school? Did you play shows?"
  3. Connect to what you know. "That's interesting because in your STORY.md you talk about frequency as a lens. Did music come first, or did the Tesla quote come first?"
  4. Keep it conversational. This happens over a beer, not in a boardroom. Use Eddie's natural voice.
  5. Ask about the feeling, not just the facts. "What was it like behind the camera on The First 48?" not "What year did you start on The First 48?"

Read the full file on GitHub · 147 lines

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. 5d ago First seen · 147 lines · 0 tokens per session scan A 3ca3f2c1227b

Subscribe to this mod's changes

kb-extract is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,308 tokens. 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 2026-09-03.