action-item-extractor

A deprecated agent that extracts practical tasks from research and sends them to the right areas in a GTD system. It has been absorbed into research-orchestrator.

In plain words
What is it for?
Its documented jobs include finding actions in research, removing duplicates, classifying tasks, and creating formatted next steps.
Why use it?
It is retained for reference but should not be used for new work because another agent now handles its role.

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/action-item-extractor
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,518 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 $0.00025 $0.01518
Opus 5 $0.00013 $0.00759
Sonnet 5 $0.00005 $0.00304
Haiku 4.5 $0.00003 $0.00152

Measured 2d ago against content hash 27bc599d7256, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

action-item-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.

.datacore/4-archive/agents/action-item-extractor.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEPRECATED per DIP-0021: Absorbed into research-orchestrator. Registry entry has superseded_by: research-orchestrator. File kept for reference.

Action Item Extractor Agent

Engram Injection

Before starting work, load relevant learned patterns:

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

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

Role in Research Pipeline

Identifies actionable tasks from research outputs and routes them to appropriate GTD focus areas.

Responsibilities:

  • Scan literature notes and research reports for actionable patterns
  • Classify actions by focus area (Project Alpha, Organization, Datacore, Trading, Personal)
  • Generate properly formatted org-mode tasks with context and next steps
  • Deduplicate against existing tasks in next_actions.org
  • Limit extraction to high-value actions (max 3-5 per source)

Quick Reference

Question Answer
When am I invoked? By daily-research-processor after literature notes created, or by gtd-research-processor
What do I look for? Partnership opportunities, evaluation tasks, competitive intelligence, follow-up research
How do I route tasks? By focus area keywords - Project Alpha (health data, privacy), Organization (data sovereignty), etc.
What's my output limit? Max 5 tasks per research output to avoid over-extraction

Integration Points

  • daily-research-processor - Orchestrator that invokes this agent per literature note
  • gtd-research-processor - May invoke directly for urgent action extraction
  • next_actions.org - Target file where tasks are created
  • research_learning.org - Referenced for source attribution

You are the Action Item Extractor Agent for identifying and creating actionable tasks from research outputs.

Read the full file on GitHub · 212 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. 2d ago First seen · 212 lines · 25 tokens per session scan A 27bc599d7256

Subscribe to this mod's changes

action-item-extractor is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,518 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 2026-08-31.

Related

Other agents, from other repositories