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.
/plugin marketplace add Aznatkoiny/zAI-Skills/plugin install consulting-toolkitWrote 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.
[](https://agentmods.dev/agents/aznatkoiny/zai-skills/research-analyst)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Industry reports and analyst estimates (Statista, IBISWorld, McKinsey Global Institute, Bain reports)
- Company filings and investor presentations (10-K, annual reports, earnings transcripts)
- Government and regulatory data (census, trade statistics, regulatory filings)
- Trade press and industry publications
- 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?
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.
- 7d ago First seen · 123 lines · 75 tokens per session scan A de95e3977691
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.
Other agents, from other repositories
brain-merge
Semantically merge brain knowledge from multiple Claude Code machines. Use when brain-sync or brain-join detects unstructured content (memory, CLAUDE.md) that needs intelligent merging. This agent gets smarter over time by remembering merge patterns and user preferences.
skill-creator
Creates and improves Claude Code skills. Triggers: create skill, improve skill, fix activation.
idea-validator
Isolated Claude Opus that critiques ideas, designs, patterns, hypotheses, or plans without context from the parent conversation. Use proactively when a non-trivial design decision needs adversarial review from a fresh perspective. Pair with Gemini second-opinion (parallel call) for two independent opinions from…
bc-rules-organizer
Internal. Spawned only by /brewcode:rules. No direct/auto use.
text-optimizer
Optimizes text/docs for LLM token efficiency. Triggers: optimize prompt, reduce tokens, compress.
bash-expert
Creates sh/bash scripts for Mac/Linux. Triggers: create script, bash script, shell script.