# research-agent-instantiation

> How to instantiate and task the research agent

- Author: NOVA
- Repository: NOVA-Openclaw/clawd-workspace
- Version: 20260207131035
- Stars: 0
- Forks: 0
- Last Updated: 2026-02-07
- Source: https://github.com/NOVA-Openclaw/clawd-workspace
- Web: https://mule.run/skillshub/@@NOVA-Openclaw/clawd-workspace~research-agent-instantiation:20260207131035

---

---
name: research-agent-instantiation
description: How to instantiate and task the research agent
---

# Research Agent Instantiation

## Tools

- `sessions_spawn`
- `psql`
- `proactive-recall.py`
- `web_search`
- `web_fetch`

## Procedure

1. GATHER TOPIC: Get clear research question or topic from user
2. CHECK EXISTING KNOWLEDGE: Run proactive-recall.py to find related memories
3. FETCH AGENT CONFIG: SELECT * FROM agents WHERE name = 'research-agent'
4. FETCH RESEARCH SOPS: SELECT name, steps FROM sops WHERE name IN ('research-methodology', 'source-reliability-assessment', 'research-citation-standards')
5. BUILD CONTEXT: Combine semantic search results + SOPs + research question
6. SPAWN AGENT: sessions_spawn(task="{context}\n\nResearch Question: {topic}", model="claude-sonnet-4-20250514", label="research-agent:{topic_slug}", cleanup="delete")
7. REVIEW: Check findings, source reliability scores, citations
8. PERSIST: Store key findings in database if significant