research

A command for carrying out broad research on a chosen topic. It searches for sources, reads the most relevant material, compares findings, and produces a structured summary.

In plain words
What is it for?
Use it to investigate technical, business, or implementation questions and collect source-backed findings, caveats, best practices, and code examples.
Why use it?
It turns a wide question into smaller research tasks and checks information across multiple sources. This reduces the work of finding, reading, and organizing background material.

Command

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/intellegix/intellegix-code-agent-toolkit/research
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
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 442 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 $0.00000 $0.00442
Opus 5 $0.00000 $0.00221
Sonnet 5 $0.00000 $0.00088
Haiku 4.5 $0.00000 $0.00044

Measured 2d ago against content hash 525cf859b5e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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.

commands/research.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research

Conduct comprehensive research on: $ARGUMENTS

Research Process

Phase 1: Initial Search

  1. Understand the query

    • Break down the research question into key concepts
    • Identify what type of information is needed (technical, business, implementation, etc.)
  2. Search for authoritative sources

    • Use WebSearch to find recent, relevant information
    • Prioritize official documentation, academic papers, and trusted technical blogs
    • Look for multiple perspectives on the topic

Phase 2: Deep Dive

  1. Fetch and analyze key sources

    • Use WebFetch to read full content from promising URLs
    • Extract relevant code examples, patterns, and best practices
    • Note any caveats, limitations, or version-specific information
  2. Cross-reference findings

    • Compare information across sources
    • Identify consensus vs. disputed approaches
    • Note any outdated information (check dates)

Phase 3: Synthesize

  1. Compile findings
    • Organize information by relevance to the original query
    • Highlight practical takeaways
    • Include code examples where applicable

Output Format

# Research: [Topic]

## Summary
[2-3 sentence executive summary]

## Key Findings

### Finding 1: [Topic]
[Details with source attribution]

### Finding 2: [Topic]
[Details with source attribution]

## Practical Recommendations
1. [Actionable recommendation]
2. [Actionable recommendation]

## Code Examples (if applicable)
```[language]
// Example implementation

Sources

  • Source 1 - [Brief description of what was learned]
  • Source 2 - [Brief description]

Caveats & Limitations

  • [Any important warnings or version-specific notes]
  • [Topic 1]
  • [Topic 2]

## Research Quality Standards
- Cite all sources with URLs
- Distinguish between facts and opinions
- Note information freshness (publication dates)
- Flag any conflicting information found
- Prefer primary sources over secondary

Read the full file on GitHub · 77 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 · 77 lines · 0 tokens per session scan A 525cf859b5e7

Subscribe to this mod's changes

research is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 442 tokens. 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 2026-08-30.