deep-research

deep-research is a command for Claude Code from PedroGiudice/lex-vector. It costs 0 tokens per session (654 once invoked), scanned A, original, MIT.

A command for researching technical topics with web searches and producing a structured report. It uses the Gemini ADK research agent and Google Search to gather information.

In plain words
What is it for?
Use it to investigate a technical question and save the resulting report in the project's research output folder.
Why use it?
It reduces the work of creating several searches, collecting results, and combining them into one technical summary.

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/pedrogiudice/lex-vector/deep-research
Clone the repo
git clone --depth 1 https://github.com/PedroGiudice/lex-vector

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 deep-research

README.md
[![agentmods](https://agentmods.dev/badge/commands/pedrogiudice/lex-vector/deep-research.svg)](https://agentmods.dev/commands/pedrogiudice/lex-vector/deep-research)
Your own site
<a href="https://agentmods.dev/commands/pedrogiudice/lex-vector/deep-research"><img src="https://agentmods.dev/badge/commands/pedrogiudice/lex-vector/deep-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 654 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 $0.00654
Opus 5 $0.00000 $0.00327
Sonnet 5 $0.00000 $0.00131
Haiku 4.5 $0.00000 $0.00065

Measured 3d ago against content hash acea762dab14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-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 3d 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.

.claude/commands/deep-research.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Command: Deep Research

Execute the Gemini ADK Deep Research Agent for autonomous technical research with web search grounding.

Usage

/deep-research "Your research topic here"

Or with arguments:

/deep-research --check   # Check dependencies only
/deep-research --help    # Show help

What This Command Does

  1. Validates that the Gemini ADK environment is properly configured
  2. Executes the Deep Research Agent with the provided topic
  3. The agent autonomously:
    • Generates multiple search queries
    • Retrieves information from the web via Google Search grounding
    • Synthesizes findings into a structured technical report
  4. Saves results to adk-agents/deep_research_sandbox/research_output/

Execution

When the user invokes this command, execute:

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "/home/cmr-auto/claude-work/repos/lex-vector")
cd "$REPO_ROOT/adk-agents" && ./run-research.sh "$ARGUMENTS"

If $ARGUMENTS is empty, ask the user for a research topic.

If $ARGUMENTS is --check, run:

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "/home/cmr-auto/claude-work/repos/lex-vector")
cd "$REPO_ROOT/adk-agents" && ./run-research.sh --check-deps

Prerequisites

  • GOOGLE_API_KEY environment variable (loaded from adk-agents/.env)
  • Python virtual environment at adk-agents/deep_research_sandbox/.venv/
  • Required packages: google-adk, google-genai, tenacity

Output Format

Research results are saved as Markdown with:

  • Key Findings: Bulleted facts with citations
  • Technical Specifications: Data tables
  • Data Conflicts / Uncertainties: Noted discrepancies
  • Source Index: Full citations

Examples

Basic research:

/deep-research "Compare vector databases: Pinecone vs Weaviate vs Milvus"

Technical analysis:

/deep-research "Latest developments in transformer attention mechanisms 2026"

Check setup:

/deep-research --check

Read the full file on GitHub · 90 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. 3d ago First seen · 90 lines · 0 tokens per session scan A acea762dab14

Subscribe to this mod's changes

deep-research is a command published in the GitHub repository PedroGiudice/lex-vector (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 654 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 2026-08-31.