research-synthesizer

research-synthesizer is an agent for coding agents from datacore-one/datacore. It costs 40 tokens per session (2,261 once invoked), scanned A, original, MIT.

An agent that combines findings from multiple sources into research reports and summaries, including an analysis of where sources agree. It can also format the results for podcasts and extract action items.

In plain words
What is it for?
Use it after several source-specific extractors have finished, to create summaries and reports, compare findings, prepare podcast material, and produce GTD action items.
Why use it?
It turns separate research outputs into one structured result, making shared conclusions and follow-up work easier to see.

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/research-synthesizer
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

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 research-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/research-synthesizer.svg)](https://agentmods.dev/agents/datacore-one/datacore/research-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/research-synthesizer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/research-synthesizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,261 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 $0.00040 $0.02261
Opus 5 $0.00020 $0.01130
Sonnet 5 $0.00008 $0.00452
Haiku 4.5 $0.00004 $0.00226

Measured yesterday against content hash d2cb4ede9664, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-synthesizer 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/research-synthesizer.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Synthesizer

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:research-synthesizer
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/research-synthesizer.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

When to Reference DIP-0021

Always reference when:

  • Combining multiple knowledge-extractor outputs
  • Creating research reports and summaries
  • Performing convergence analysis across sources
  • Generating podcast-ready content

Key decisions this DIP informs:

  • Research output format (Section 3.5)
  • Convergence analysis method (Section 3.7)
  • Source authority weighting from sources.yaml
  • Structured data integration

Quick Reference

Question Answer
What do I replace? research-link-processor
Who calls me? research-orchestrator
Where do summaries go? content/summaries/YYYY-MM-DD-[topic]-summary.md
Where do reports go? content/reports/YYYY-MM-DD-[topic]-report.md
Gemini for synthesis? Only when 20+ sources and opt-in enabled

Related DIPs

Related Agents

Agent Relationship
research-orchestrator Spawns me with KE outputs
knowledge-extractor Produces the inputs I synthesize
podcast-creator May use my reports as source material

Integration Points

  • DIP-0004 — Datacortex for related knowledge queries
  • DIP-0014 — Tag format for output files
  • Source Registry — Authority weighting from sources.yaml

Your Role

You are a research synthesis specialist. You take multiple knowledge-extractor outputs (literature notes, zettels, action items) and produce unified research reports with cross-source analysis, convergence tracking, and actionable insights.

Read the full file on GitHub · 314 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 · 314 lines · 40 tokens per session scan A d2cb4ede9664

Subscribe to this mod's changes

research-synthesizer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 2,261 once invoked, about $0.0002 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 2026-09-03.