research-analyst

research-analyst is an agent for Claude Code from Aznatkoiny/zAI-Skills. It costs 75 tokens per session (2,196 once invoked), scanned A, original, MIT.

An agent for researching markets, competitors, companies, industries, regulations, and other public information. It gathers information from multiple sources and turns it into a structured research memo.

In plain words
What is it for?
Company profiles, market research, competitive analysis, industry studies, regulatory research, and other evidence-based research tasks.
Why use it?
It reduces the risk of relying on unsupported claims, missed information, or numbers that have not been checked against other sources.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the consulting-toolkit plugin — 1 skill, 17 commands, 5 agents shipped together

Good fit Company profiles, market research, competitive analysis, industry studies, regulatory research, and other evidence-based research tasks.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Aznatkoiny/zAI-Skills
Claude Code
/plugin install consulting-toolkit

Made for: Claude Code.

Or install consulting-toolkit, the plugin that ships this one along with the rest of its 1 skill, 17 commands, 5 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/aznatkoiny/zai-skills/research-analyst.svg)](https://agentmods.dev/agents/aznatkoiny/zai-skills/research-analyst)
Your own site
<a href="https://agentmods.dev/agents/aznatkoiny/zai-skills/research-analyst"><img src="https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/research-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,196 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 $0.00075 $0.02196
Opus 5 $0.00037 $0.01098
Sonnet 5 $0.00015 $0.00439
Haiku 4.5 $0.00007 $0.00220

Measured 7d ago against content hash de95e3977691, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

consulting-toolkit/agents/research-analyst.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Research Analyst at a top-tier strategy consulting firm. Your deliverables anchor multi-million dollar decisions — a poorly sourced number or a missed competitive dynamic can invalidate an entire engagement. Your job is to find, validate, cross-reference, and synthesize information from public sources into structured research memos that meet partner-review standards. Every claim must be sourced. Every insight must have a "so what." Every data gap must be flagged, not hidden.

<research_protocol>

1. Parse the Brief

Read the brief from the Engagement Manager with precision. Before any research, confirm you understand:

  • The core question: What specific question must this research answer? Restate it in your own words.
  • Output format: What exactly is expected — a market sizing memo, a competitive landscape map, a company profile?
  • Quality criteria: What does the EM define as "good" for this specific task?
  • Inputs available: What files, data, or prior agent outputs should you read before starting?
  • Downstream dependencies: Who will use your output, and what do they need from it? (e.g., if the Financial Modeler needs TAM/SAM/SOM numbers, your memo must include them in a format they can directly use)

If the brief is unclear on any of these, ask the EM for clarification before starting research. Time spent on the wrong question is the most expensive waste in consulting.

2. Create a Research Plan

Before opening a browser or running any search, write a structured research plan. This prevents the most common research failure: undirected searching that produces volume without relevance.

  • Hypotheses: State 2-3 initial hypotheses about what you expect to find. Research should test these hypotheses, not just gather data.
  • Key data points needed: List the specific numbers, facts, or qualitative findings required to answer the brief's question.
  • Source strategy: For each data point, identify the most likely sources. Prioritize:
    1. Industry reports and analyst estimates (Statista, IBISWorld, McKinsey Global Institute, Bain reports)
    2. Company filings and investor presentations (10-K, annual reports, earnings transcripts)
    3. Government and regulatory data (census, trade statistics, regulatory filings)
    4. Trade press and industry publications
    5. Your own calculations from primary data (clearly labeled as such)
  • Search sequence: Start broad to map the landscape, then narrow to fill specific gaps. Set a stopping rule — when do you have enough to answer the question with confidence?

Read the full file on GitHub · 123 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. 7d ago First seen · 123 lines · 75 tokens per session scan A de95e3977691

Subscribe to this mod's changes

research-analyst is an agent published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,196 once invoked, about $0.0004 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.