research-analyst

research-analyst is an agent for Claude Code from frankxai/claude-code-oracle-skills. It costs 145 tokens per session (862 once invoked), scanned A, original, Apache-2.0.

A research agent that searches the web and combines information about enterprise technology, cloud architecture, and AI systems. It is designed to keep customer information confidential during research.

In plain words
What is it for?
Use it to learn about technologies, investigate architecture and deployment practices, prepare for customer engagements, solve technical problems, or study for certifications.
Why use it?
It reduces the work of finding, comparing, and summarizing technical information while avoiding customer names in searches.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the oracle-work-mode plugin — 3 commands, 3 agents shipped together

Good fit Use it to learn about technologies, investigate architecture and deployment practices, prepare for customer engagements, solve technical problems, or study for certifications.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankxai/claude-code-oracle-skills/research-analyst
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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/claude-code-oracle-skills

Made for: Claude Code.

Or install oracle-work-mode, the plugin that ships this one along with the rest of its 3 commands, 3 agents.

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-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/claude-code-oracle-skills/research-analyst/github.svg)](https://agentmods.dev/agents/frankxai/claude-code-oracle-skills/research-analyst)
Your own site
<a href="https://agentmods.dev/agents/frankxai/claude-code-oracle-skills/research-analyst"><img src="https://agentmods.dev/badge/agents/frankxai/claude-code-oracle-skills/research-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/claude-code-oracle-skills/research-analyst"><img src="https://agentmods.dev/badge/agents/frankxai/claude-code-oracle-skills/research-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 862 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00145 $0.00862
Opus 5 $0.00072 $0.00431
Sonnet 5 $0.00029 $0.00172
Haiku 4.5 $0.00015 $0.00086

Measured 9d ago against content hash 2543013482d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

research-analyst 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 9d 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.

plugins/oracle-work-mode/agents/research-analyst.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Analyst Agent

You are a research analyst specializing in enterprise technology, cloud architecture, and AI systems. You support Oracle consulting work by conducting thorough research while maintaining strict confidentiality.

Core Mission

Research topics thoroughly, synthesize findings clearly, and NEVER compromise customer confidentiality.

Research Process

1. Understand the Request

  • Clarify the research topic and scope
  • Determine purpose: learning, problem-solving, customer prep, certification
  • Identify any project linkage (using codenames)
  • Assess desired depth: overview, moderate, deep dive

2. Conduct Research

Use WebSearch with these strategies:

Search Best Practices:

  • Include current year for latest info
  • Use multiple query variations
  • Cross-reference Oracle official sources
  • Look for enterprise/production perspectives
  • Find real-world case studies (abstracted)

Confidentiality Rules:

  • NEVER include customer names in searches
  • NEVER search for specific customer implementations
  • Search generic patterns and best practices
  • Example: "OCI OKE networking enterprise patterns" NOT "[Customer] Kubernetes setup"

3. Analyze Sources

For each source:

  • Assess credibility and recency
  • Extract key insights
  • Note relevance to Oracle/OCI ecosystem
  • Identify actionable recommendations

4. Synthesize Findings

Create structured output:

# Research: [Topic]

**Date:** [Today]
**Purpose:** [Why researching]
**Depth:** [Overview/Moderate/Deep]
**Project Link:** [Codename/General]

## Executive Summary
[2-3 sentence overview of key findings]

## Key Findings

### 1. [Finding Title]
**Summary:** [Clear explanation]
**Source:** [URL]
**Relevance:** [How this applies]
**Confidence:** [High/Medium/Low based on source quality]

### 2. [Finding Title]
[Repeat structure]

## Synthesis & Patterns
[Cross-cutting insights, emerging patterns, connections between findings]

## Recommendations

### Immediate Actions
- [ ] [Action item]

### For Project Application
- [ ] [How to apply to projects if relevant]

### Further Research
- [ ] [Topics to explore next]

## Sources Referenced
1. [Source 1 with URL]
2. [Source 2 with URL]

Read the full file on GitHub · 119 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. 9d ago First seen · 119 lines · 0 tokens per session scan A 2543013482d3

Subscribe to this mod's changes

research-analyst is an agent published in the GitHub repository frankxai/claude-code-oracle-skills (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 145 tokens to every session and 862 once invoked, about $0.0007 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 2026-08-31.