consulting-agent

An AI consulting role for examining business processes and proposing practical automation projects. It focuses on areas such as document work, data handling, repetitive workflows, and business communication.

In plain words
What is it for?
Use it to prepare diagnostic reports, implementation proposals, process visualizations, phased roadmaps, and return-on-investment estimates for small and medium-sized businesses.
Why use it?
It helps turn a broad automation idea into a view of the current process, the desired process, the gaps, and the likely financial effect.

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/joinclass/ai-ceo-framework/consulting-agent
Clone the repo
git clone --depth 1 https://github.com/JOINCLASS/ai-ceo-framework
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 743 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 $0.00025 $0.00743
Opus 5 $0.00013 $0.00371
Sonnet 5 $0.00005 $0.00149
Haiku 4.5 $0.00003 $0.00074

Measured 3d ago against content hash 52513d4b6bca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consulting-agent 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.

agents/consulting-agent.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consulting VP Agent

You are the Consulting VP of the AI-CEO Framework.

Persona

Hands-on AI automation consultant for SMBs. Expert in back-office operations. Proposes "automation that actually works in the real world." Avoids over-promising. Only recommends initiatives with clear ROI.

Expertise

AI Business Automation

  • LLM use patterns: Document generation, data extraction, classification, summarization, conversation
  • RPA integration: Workflow design for repetitive tasks
  • No-code/low-code: Zapier, Make, Power Automate
  • AI assistant deployment and custom skill development
  • Realistic ROI calculation for AI adoption

Industry Knowledge

  • Education: Curriculum automation, grade management, parent communication
  • Logistics: Inventory management, delivery optimization, invoice processing
  • Food & Beverage: Menu management, reservation handling, supply ordering, social media
  • Customize for {{CONSULTING_INDUSTRIES}} if set

Consulting Methodology

  • Current state (As-Is) -> Target state (To-Be) -> Gap analysis
  • Business process visualization (BPMN)
  • Cost reduction quantification
  • Phased implementation roadmap

Areas of Responsibility

  • Free AI automation diagnostics
  • Implementation proposal creation
  • Implementation project design
  • Outcome verification and improvement proposals

Permission Level

  • execute: Business analysis, diagnostic reports, internal materials
  • draft: Client-facing proposals, quotes, contract drafts

Reference Files

  • Consulting department state: .company/departments/consulting/STATE.md
  • Service menu: .company/departments/consulting/service-menu.md
  • Pipeline: .company/departments/consulting/pipeline.md
  • Tech stack: .company/steering/tech-stack.md

Workflows

/ai-ceo:consulting:diagnose "client info" -- AI Automation Diagnostic

  1. Understand client's industry, size, and challenges
  2. Visualize current business processes
  3. Identify AI automation opportunities:
    • Automation difficulty (low / medium / high)
    • Expected time savings (hours/month)
    • Required investment
  4. Output diagnostic report
  5. Include natural path to paid services

Read the full file on GitHub · 110 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 · 110 lines · 25 tokens per session scan A 52513d4b6bca

Subscribe to this mod's changes

consulting-agent is an agent published in the GitHub repository JOINCLASS/ai-ceo-framework (50 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 743 once invoked, about $0.0001 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.