research

research is a command for Claude Code from jwynia/context-networks. It costs 0 tokens per session (2,824 once invoked), scanned B, original, MIT.

A research command that guides an AI assistant through planning, finding existing project knowledge, identifying gaps, and organizing findings in a context network. The topic is supplied as an argument.

In plain words
What is it for?
Use it to investigate a topic, review related project research, define questions, record discoveries, and produce a structured synthesis.
Why use it?
It helps prevent duplicated research and keeps research notes and reports organized away from implementation files.

Command for Claude Code

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 commands/jwynia/context-networks/research
Clone the repo
git clone --depth 1 https://github.com/jwynia/context-networks

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/jwynia/context-networks/research.svg)](https://agentmods.dev/commands/jwynia/context-networks/research)
Your own site
<a href="https://agentmods.dev/commands/jwynia/context-networks/research"><img src="https://agentmods.dev/badge/commands/jwynia/context-networks/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,824 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.02824
Opus 5 $0.00000 $0.01412
Sonnet 5 $0.00000 $0.00565
Haiku 4.5 $0.00000 $0.00282

Measured 4d ago against content hash 9468a314fbe2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

research scanned grade B with 1 finding 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 4d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

## Output Instructions
.claude/commands/research.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Integration Context Network Agent Prompt

Task Context

You are conducting research using the Research MCP server on the topic: $ARGUMENTS

Your goal is to perform comprehensive research and integrate all findings, analysis, and insights into the context network following proper organizational principles.

Critical Domain Boundary

REMEMBER: All research outputs, analysis documents, and synthesis reports MUST be placed in the context network, NOT in the project root. Only implementation artifacts belong outside the context network.

Research Execution Process

Phase 1: Research Planning & Context Discovery

  1. Parse Research Scope

    Topic: $ARGUMENTS
    
    • Identify key concepts and domains to explore
    • Determine research depth needed (exploratory vs. deep dive)
    • List specific questions to answer
  2. Context Network Reconnaissance

    • Search existing context network for related research
    • Check discovery records for related insights (/discoveries/records/)
    • Review learning paths for context evolution (/learning-paths/)
    • Identify relevant domain nodes
    • Map existing knowledge to avoid duplication
    • Note gaps the research should fill
  3. Research Strategy

    • Define search queries for Research MCP
    • Plan research phases (broad → specific)
    • Set criteria for source evaluation
    • Establish synthesis approach
    • Create a research report file named with the freshly verified current date and topic in the context network.

Phase 2: Research Execution

  1. Initial Broad Research

    mcp.research("$ARGUMENTS overview current state")
    mcp.research("$ARGUMENTS key concepts definitions")
    mcp.research("$ARGUMENTS major approaches methods")
    
  2. Domain-Specific Deep Dives Based on initial findings, explore specific aspects:

    • Technical implementations
    • Theoretical foundations
    • Practical applications
    • Case studies/examples
    • Limitations/challenges

Read the full file on GitHub · 394 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. 4d ago First seen · 394 lines · 0 tokens per session scan B 9468a314fbe2

Subscribe to this mod's changes

research is a command published in the GitHub repository jwynia/context-networks (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,824 tokens. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.