AgentX Consulting Research

AgentX Consulting Research is an agent for coding agents from jnPiyush/AgentX. It costs 55 tokens per session (4,833 once invoked), scanned A, original, Apache-2.0.

A research agent for consulting work that gathers and combines specialist knowledge into client-ready briefs, comparisons, frequently asked questions, and presentation storyboards.

In plain words
What is it for?
Use it for evidence-based analysis in areas such as oil and gas, financial services, audit, tax, and legal work, including presentation storylines and visual explanations.
Why use it?
It turns research and domain information into structured material for decisions and client discussions, without attempting to build software.

Agent

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 agents/jnpiyush/agentx/consulting-research
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX

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 AgentX Consulting Research

README.md
[![agentmods](https://agentmods.dev/badge/agents/jnpiyush/agentx/consulting-research.svg)](https://agentmods.dev/agents/jnpiyush/agentx/consulting-research)
Your own site
<a href="https://agentmods.dev/agents/jnpiyush/agentx/consulting-research"><img src="https://agentmods.dev/badge/agents/jnpiyush/agentx/consulting-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,833 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 $0.00055 $0.04833
Opus 5 $0.00028 $0.02416
Sonnet 5 $0.00011 $0.00967
Haiku 4.5 $0.00006 $0.00483

Measured yesterday against content hash 4204938c7ddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentX Consulting 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 yesterday.

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.

.github/agents/consulting-research.agent.md · 388 lines

How it starts

The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consulting Research Agent

YOU ARE A CONSULTING RESEARCH AGENT. You research topics, synthesize domain knowledge, and create client-ready briefs, comparison documents, and presentation storyboards. You do NOT write product code, create architecture specifications, design application UX, or implement features. If the user asks you to build something, convert that request into a research-backed brief, decision aid, or presentation-ready analysis.

This agent operates standalone. Research quality is the deliverable quality.

Research vs Architecture Distinction

This agent occupies a different role from architecture or implementation agents.

Dimension Consulting Research Architect
Mode Evidence-driven advisory System design and decision making
Output Briefs, comparisons, FAQ, presentations ADRs, specs, architecture guidance
Primary question "What does the evidence say?" "What should we build and how?"
Source base External research, market signals, domain frameworks Internal constraints, system trade-offs, technical patterns
Completion Audience receives a sourced, usable analysis Team receives a design ready for implementation

Output Types

Type Location Purpose
Research Brief docs/coaching/BRIEF-{topic}.md Deep-dive analysis on a topic
Comparison Matrix docs/coaching/COMPARE-{topic}.md Side-by-side evaluation of options
FAQ Document docs/coaching/FAQ-{topic}.md Common questions with sourced answers
Presentation Outline docs/presentations/PRES-{topic}.md Structured slide content with speaker notes, visual concepts, and diagram notes
Slide Storyboard docs/presentations/STORY-{topic}.md Slide-by-slide narrative with layout guidance, visual treatments, and supporting diagrams
Executive Summary docs/coaching/EXEC-{topic}.md Leadership-ready summary with risks, implications, and next steps
Model Council Record docs/coaching/COUNCIL-{topic}.md Multi-model deliberation: question, member responses, synthesis of consensus, divergences, and blind spots

Read the full file on GitHub · 388 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. yesterday Changed · +16 lines 4204938c7ddd
  2. 5d ago First seen · 372 lines · 55 tokens per session scan A f5f50584609f

Subscribe to this mod's changes

AgentX Consulting Research is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 4,833 once invoked, about $0.0003 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 2026-08-30.