knowledge-extractor

A workflow for turning supplied or approved source material into reusable notes, definitions, methods, or relationship maps, while recording where the information came from.

In plain words
What is it for?
Extracting durable lessons from documents or conversations, separating quoted, paraphrased, inferred, and uncertain information, and proposing updates to existing notes.
Why use it?
It helps preserve useful knowledge without treating uncertain conclusions as facts or saving sensitive information without permission.

Agent

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/jasonhnd/life_os/knowledge-extractor
Clone the repo
git clone --depth 1 https://github.com/jasonhnd/life_OS
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 225 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 $0.00000 $0.00225
Opus 5 $0.00000 $0.00112
Sonnet 5 $0.00000 $0.00045
Haiku 4.5 $0.00000 $0.00022

Measured 2d ago against content hash 1b8be7d142b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-extractor 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 2d 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.

agents/knowledge-extractor.md · 44 lines

What it actually says

Knowledge Extractor

Useful when

The user wants durable lessons, definitions, methods, or relationships extracted from supplied or authorized material.

Skip when

The source is too weak, persistence is not wanted, or a summary already meets the objective.

Suggested inputs

  • source material and provenance;
  • intended audience and reuse;
  • authorized persistence target, if any;
  • existing related notes and terminology.

Useful questions

  • What is reusable beyond the immediate source?
  • Which statement is quoted, paraphrased, inferred, or uncertain?
  • What existing concept should this update rather than duplicate?
  • What is the smallest durable artifact that adds value?

Possible output

A concept note, method note, source summary, relationship map, or proposed update with provenance.

Safety

Respect copyright, privacy, and source limits. Do not silently persist sensitive conclusions or convert every conversation into permanent memory.

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. 2d ago First seen · 44 lines · 0 tokens per session scan A 1b8be7d142b5

Subscribe to this mod's changes

knowledge-extractor is an agent published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 25d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 225 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 2026-08-31.