gtd-research-processor

An autonomous research agent that fetches web URLs, analyses their content, and creates structured literature notes and atomic zettels. A zettel is a small, reusable knowledge note linked to related notes.

In plain words
What is it for?
Process research URLs, summarise important findings, create linked knowledge notes, assess relevance, and identify possible action items.
Why use it?
It turns source pages into organised summaries and reusable ideas instead of leaving research scattered across webpages and temporary notes.

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/gtd-research-processor-module
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,951 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 $0.00050 $0.04951
Opus 5 $0.00025 $0.02475
Sonnet 5 $0.00010 $0.00990
Haiku 4.5 $0.00005 $0.00495

Measured 2d ago against content hash 84df2067a782, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gtd-research-processor 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/gtd-research-processor-module.md · 724 lines

How it starts

The opening of the file, as written. The whole thing — 724 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GTD Research Processor - Autonomous Research 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:gtd-research-processor
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/gtd-research-processor.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

Role in Research Pipeline

Autonomous URL analyzer that fetches content, creates literature notes with progressive summarization, and generates atomic zettels for knowledge integration.

Responsibilities:

  • Fetch and analyze URLs from research tasks or research_learning.org
  • Create structured literature notes with L1 (summary) and L2 (key insights) layers
  • Extract atomic concepts and generate zettel notes for reusable knowledge
  • Link new content to existing notes in knowledge base
  • Assess relevance to work areas (Project Alpha, Organization, Datacore, Trading, Personal)
  • Identify actionable takeaways for action-item-extractor
  • Handle URL failures gracefully with retry strategies
  • Return structured output for downstream processing

Quick Reference

Question Answer
When am I invoked? By ai-task-executor for :AI:research: tasks, or by daily-research-processor per URL
What do I create? Literature notes in 2-knowledge/literature/ and zettels in 2-knowledge/zettel/
What format? Obsidian markdown with frontmatter, wiki-links, progressive summarization
How many zettels per source? 1-3 atomic concepts (only when truly reusable)
What if URL fails? Try archive.org fallback, return detailed failure report with alternatives

Integration Points

  • ai-task-executor - Routes :AI:research: tagged tasks to this agent
  • daily-research-processor - Invokes this agent for each research URL during nightshift
  • action-item-extractor - Consumes key insights and actionable takeaways from output
  • research-post-processor - Uses literature note and zettel paths for org updates
  • CRM module - research_complete hook triggered with entity mentions
  • Obsidian knowledge base - Literature notes and zettels integrate via wiki-links

Read the full file on GitHub · 724 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 · 724 lines · 0 tokens per session scan A 84df2067a782

Subscribe to this mod's changes

gtd-research-processor is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 4,951 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

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

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