knowledge-extractor

A coordinator that turns source material—such as web pages, PDFs, conversations, files, or text—into organized knowledge records. It routes each input to specialized helper agents and can create literature notes, small linked notes, and action items.

In plain words
What is it for?
Use it to process research or other content, create structured notes, extract key insights, produce action items, and route work to the appropriate helper agent.
Why use it?
It removes the need to decide manually how each kind of source should be processed. It also keeps the resulting notes and tasks in a consistent structure.

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/datacore-one/datacore/knowledge-extractor
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,359 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 $0.00051 $0.03359
Opus 5 $0.00026 $0.01680
Sonnet 5 $0.00010 $0.00672
Haiku 4.5 $0.00005 $0.00336

Measured yesterday against content hash 1ff660878505, 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 yesterday.

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.

.datacore/agents/knowledge-extractor.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Extractor

Engram Injection

Before starting work, load relevant learned patterns:

  1. Preferred: Call plur_admin MCP tool with action = "plur_inject_hybrid", prompt = your task description, scope = agent:knowledge-extractor
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/knowledge-extractor.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

When to Reference DIP-0021

Always reference when:

  • Processing any content into knowledge artifacts
  • Routing content to sub-agents
  • Creating literature notes or zettels
  • Determining output paths and formats

Key decisions this DIP informs:

  • Which sub-agent handles which input type
  • Literature note format (L1 summary + L2 key insights)
  • Zettel atomicity criteria
  • Output JSON format for callers
  • Source registry for Jina availability

Quick Reference

Question Answer
What do I replace? gtd-research-processor, ingest-processor, conversation-processor
Who calls me? research-orchestrator, ingest-orchestrator, ai-task-executor
Sub-agents? url-fetcher, pdf-extractor, conversation-parser, file-reader
MCP tools? research.transcribe_youtube (YouTube extraction)
Literature notes? [space]/3-knowledge/literature/
Zettels? [space]/3-knowledge/zettel/
Dedup check? datacortex search before creating

Related DIPs

Related Agents

Agent Relationship
url-fetcher Sub-agent: fetches web content
research.transcribe_youtube MCP tool: extracts YouTube transcripts (replaced youtube-transcriber agent)
pdf-extractor Sub-agent: extracts PDF content
conversation-parser Sub-agent: parses dialogue exports
file-reader Sub-agent: reads local files
tag-suggester Called for tag generation
research-orchestrator Spawns me for research pipelines
ingest-orchestrator Spawns me for file ingestion
ai-task-executor Routes :AI:research: tasks to me (via research-orchestrator)

Read the full file on GitHub · 428 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. yesterday First seen · 428 lines · 51 tokens per session scan A 1ff660878505

Subscribe to this mod's changes

knowledge-extractor is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 3,359 once invoked, about $0.0003 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 2026-08-31.

Related

Other agents, from other repositories

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

verification-gate

Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…

sliamh11/Deus · 111 tokens

keystone

Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…

sliamh11/Deus · 87 tokens

brainstormer

Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…

sliamh11/Deus · 210 tokens

code-reviewer

Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…

sliamh11/Deus · 222 tokens