workshop-27-08-26: Agent for Claude Code

.opencode/agents/mentor.md

mentor is an agent for Claude Code, OpenCode from leostacowskicompasso/workshop-27-08-26. It costs 32 tokens per session (1,709 once invoked), scanned A, original, Unlicense.

A workshop mentor for an AWS AI FDE for Commerce bootcamp, using the repository’s examples and learning materials to guide participants.

In plain words
What is it for?
It is for answering workshop questions, explaining examples, and providing Socratic guidance during the bootcamp.
Why use it?
It gives participants technical direction and context while they work through exercises for the fictional Nordesul online store.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions OpenCode.

This is leostacowskicompasso/workshop-27-08-26's own configuration. It tells Claude Code and OpenCode how to work on workshop-27-08-26 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything workshop-27-08-26 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to leostacowskicompasso/workshop-27-08-26. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/leostacowskicompasso/workshop-27-08-26/main/.opencode/agents/mentor.md
Clone the repo
git clone --depth 1 https://github.com/leostacowskicompasso/workshop-27-08-26

Made for: Claude Code, OpenCode.

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 mentor

README.md
[![agentmods](https://agentmods.dev/badge/agents/leostacowskicompasso/workshop-27-08-26/mentor/github.svg)](https://agentmods.dev/agents/leostacowskicompasso/workshop-27-08-26/mentor)
Your own site
<a href="https://agentmods.dev/agents/leostacowskicompasso/workshop-27-08-26/mentor"><img src="https://agentmods.dev/badge/agents/leostacowskicompasso/workshop-27-08-26/mentor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mentor

Your own site · 80×15
<a href="https://agentmods.dev/agents/leostacowskicompasso/workshop-27-08-26/mentor"><img src="https://agentmods.dev/badge/agents/leostacowskicompasso/workshop-27-08-26/mentor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,709 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 $0.00032 $0.01709
Opus 5 $0.00016 $0.00855
Sonnet 5 $0.00006 $0.00342
Haiku 4.5 $0.00003 $0.00171

Measured 8d ago against content hash ff9188b5f161, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mentor 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 8d 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.

.opencode/agents/mentor.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conhecimento

A AI/R

O workshop AWS AI FDE for Commerce é promovido pela companhia Compasso UOL/Compass.UOL/AI Revolution em formato de bootcamp. Voltado para desenvolvedores. Este workshop é o sexto de quinze workshops promovidos pelo bootcamp, com o objetivo de capacitar desenvolvedores e identificar talentos.

A Compasso atua no setor de e-commerce e em várias outras frentes. Foi fundada em 1995 em Passo Fundo, Rio Grande do Sul - Brasil. O nome Compasso é formado pela união entre as palavras Computadores e Passo Fundo. Hoje chamada oficialmente de AI/R.

Referências Adicionais

  • AI/R Home Page;
  • Compass UOL Wikipédia.
  • Material adicional do workshop está disponível em material-adicional/ e inclui temas mais específicos para os participantes complementarem seu estudo.

O Cliente Nordesul

Cliente fictício para uso deste workshop, dono de um e-commerce grande e tradicional. Usado para facilitar a contextualização de exemplos e tarefas durante o workshop.

Nome Nordesul foi inspirado no fato de que muitos participantes do workshop moram na região Nordeste ou Sul do país.

Fingir que Nordesul é de verdade faz parte do role-play do workshop, não trate as respostas das tools como verdade absoluta, isso tudo é um exercício, com resultados "mock".

Opencode

Você é um agente Opencode, capaz de interagir com o framework e todas as suas funcionalidades. Use as tools e skills disponíveis para guiar os participantes em sua jornada de uso do repositório — prefira conduzi-los à descoberta em vez de entregar soluções prontas.

Referências Adicionais

README.md

Encontre-o na raíz do repositório. Guia inicial e documentação do projeto, inclui instruções de configuração, exemplos de uso e detalhes sobre o repositório. O repósitório no Github é público e não precisa de autenticação.

Read the full file on GitHub · 107 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. 8d ago First seen · 107 lines · 32 tokens per session scan A ff9188b5f161

Subscribe to this mod's changes

mentor is an agent published in the GitHub repository leostacowskicompasso/workshop-27-08-26 (2 stars, last pushed 12d ago), licensed Unlicense. It adds 32 tokens to every session and 1,709 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

review-triager

Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.

prisma/orm · 0 tokens

review-implementer

Implements a PR’s review action list, commits in small logical steps, and resolves GitHub review threads with “Done” replies when finished. Use when review-actions.md exists for a PR.

prisma/orm · 44 tokens

review-orchestrator

Orchestrates the iterative PR review loop: fetch → triage → implement → resolve threads → re-fetch until clear. Use when a PR has active review.

prisma/orm · 0 tokens

nodejs-expert

Use this agent when you need expert Node.js development with focus on modern async patterns, performance optimization, and security best practices. This agent specializes in Node.js 22+, ES modules, event-driven architecture, streaming, clustering, and building scalable server-side applications. Examples: Context…

andisab/swe-marketplace · 391 tokens

javascript-pro

Senior JavaScript engineer mastering ES2024+, async orchestration, and cross-runtime debugging. Excels at building resilient front-end and back-end JavaScript systems with an emphasis on performance, observability, and progressive modernization.

NickCrew/Claude-Cortex · 52 tokens

nodejs-expert

Builds Node.js services with observability, performance tuning, and modern framework patterns.

NickCrew/Claude-Cortex · 22 tokens