setup

A setup command for Agentic Buddy, a system that keeps an agent profile, user information, projects, and domain-specific instructions. It either performs first-time setup or guides changes to an existing setup.

In plain words
What is it for?
Use it to initialize the system, update a user profile, add a project, apply a domain pack, or review the existing structure.
Why use it?
It prevents an already-configured system from being overwritten and makes the setup conversation and generated files follow the chosen language rules.

Command for Cursor

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 commands/juanje/agentic-buddy/setup
Clone the repo
git clone --depth 1 https://github.com/juanje/agentic-buddy

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,939 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00000 $0.01939
Opus 5 $0.00000 $0.00970
Sonnet 5 $0.00000 $0.00388
Haiku 4.5 $0.00000 $0.00194

Measured yesterday against content hash 121a6f31e696, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

setup scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf templates/
.cursor/commands/setup.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the Agentic Buddy setup.

If a language is specified after the command (e.g., /setup español), conduct the entire setup conversation in that language. If no language is specified, detect the user's language from their first response and continue in that language. All generated content (files, notes, logs) is always in English regardless of conversation language.

Pre-flight check

First, determine if this is a fresh setup or a reconfiguration:

  1. Read CLAUDE.md.

  2. If it contains POST-SETUP:Fresh setup. Proceed with the full setup below.

  3. If it does NOT contain that marker → System already configured. Switch to reconfiguration mode:

    The system is already set up. I can help you with:

    • Update your profile (agent_brain/identity/USER.md)
    • Add a new project to agent_brain/projects/
    • Apply a domain pack (see .packs/index.md)
    • Review or adjust the current structure

    What would you like to update?

    In reconfiguration mode: never overwrite CLAUDE.md. Only modify the specific files the user asks about.

    After changes, commit: git add -A && git commit -m "reconfig: <what changed>"

    Do not continue with the steps below. End here for reconfiguration.


Full setup procedure

Step 1: Introduction

Read templates/CLAUDE.md to understand the system you're setting up (don't explain the whole system to the user).

Then tell the user (in their language):

I'll help you set up your Agentic Buddy. I'll ask a few questions to personalize the system. It takes about 2 minutes.

After that, the system is ready. You can start brain-dumping tasks, ideas, notes, and anything else right away.

Step 2: Get to know the user

Start with a warm, conversational tone. This is a first meeting — get to know the person. Ask one group at a time, wait for answers, and adapt naturally.

Who are you and what do you need? (ask all of these together)

  • What's your name?
  • What do you want to use this for? (open-ended — let them describe it in their own words: work, personal projects, writing, training, anything)
  • Anything else you'd like to share? How you like to work, what matters to you, how you prefer information presented... Whatever feels relevant. (This is optional and open — some people share a lot, others prefer to keep it brief. Both are fine.)

Read the full file on GitHub · 156 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 First seen · 156 lines · 0 tokens per session scan C 121a6f31e696

Subscribe to this mod's changes

setup is a command published in the GitHub repository juanje/agentic-buddy (11 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,939 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.