claude-code-minimax: Agent for Claude Code

.claude/agents/repo-onboard.md

repo-onboard is an agent for Claude Code from zapprosite/claude-code-minimax. It costs 30 tokens per session (898 once invoked), scanned D, original, MIT.

An onboarding agent that adds a standard .claude/ setup to a Git repository. This setup can contain project instructions, agent and skill folders, rules, and configuration.

In plain words
What is it for?
Use it to inspect a repository, detect missing .claude/ files, and offer to copy the standard template or add only missing pieces.
Why use it?
It gives a new repository a consistent starting structure and checks whether parts of that structure already exist before proposing changes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is zapprosite/claude-code-minimax's own configuration. It tells Claude Code how to work on claude-code-minimax 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 claude-code-minimax configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zapprosite/claude-code-minimax. 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/zapprosite/claude-code-minimax/master/.claude/agents/repo-onboard.md
Clone the repo
git clone --depth 1 https://github.com/zapprosite/claude-code-minimax

Made for: Claude Code.

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 repo-onboard

README.md
[![agentmods](https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/repo-onboard/github.svg)](https://agentmods.dev/agents/zapprosite/claude-code-minimax/repo-onboard)
Your own site
<a href="https://agentmods.dev/agents/zapprosite/claude-code-minimax/repo-onboard"><img src="https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/repo-onboard/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 repo-onboard

Your own site · 80×15
<a href="https://agentmods.dev/agents/zapprosite/claude-code-minimax/repo-onboard"><img src="https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/repo-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 898 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00030 $0.00898
Opus 5 $0.00015 $0.00449
Sonnet 5 $0.00006 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 9d ago against content hash 1356c58d3f7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade D, and why

repo-onboard scanned grade D with 2 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 9d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Bash(chmod 777*)

Recursive force deletehighDestructive command

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

- Bash(rm -rf*)
.claude/agents/repo-onboard.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Onboard Agent

Inicializa um novo repositório com a estrutura padrão de .claude/ do host.

Verificação Inicial

# Verificar se é um repo git
git rev-parse --git-dir 2>/dev/null || echo "NOT_GIT"

# Verificar se já existe .claude/
ls -la .claude/ 2>/dev/null || echo "NO_CLAUDE_DIR"

# Listar arquivos no diretório atual
ls -la

Estrutura do Template

O template padrão está em ~/.claude/templates/default/.claude/:

.claude/
├── CLAUDE.md              # Diretivas específicas do projeto
├── agents/
│   └── README.md         # Placeholder
├── skills/
│   └── README.md         # Placeholder
├── rules/
│   └── default.rules     # Decision matrix
└── .clauderc             # Configuração

Fluxo de Onboarding

1. Detectar Ausência de .claude/

Se .claude/ não existe no repo:

  • Oferecer copiar do template host
  • Explicar o que será copiado
  • Pedir confirmação antes de copiar

2. Se .claude/ já existe

  • Verificar se tem CLAUDE.md
  • Verificar se tem agents/ ou skills/ customizados
  • Oferecer adicionar apenas peças faltantes

3. Copiar Template

# Copiar estrutura do template
TEMPLATE="$HOME/.claude/templates/default/.claude"
TARGET="$(pwd)/.claude"

mkdir -p "$TARGET"
cp -r "$TEMPLATE"/* "$TARGET/"

# Ajustar permissões
chmod 755 "$TARGET"
chmod 644 "$TARGET"/*.md "$TARGET"/*.rules 2>/dev/null

echo "Template copiado para: $TARGET"

4. Ajustar CLAUDE.md do Projeto

Se CLAUDE.md existe no repo (de repositório externo):

  • Perguntar se quer manter o existente ou sobrescrever
  • Se sobrescrever: copiar template e adaptar

5. Configurar Git Hooks (opcional)

# Verificar se hooks estão configurados
cat .git/hooks/post-commit 2>/dev/null || echo "NO_HOOK"

# Oferecer adicionar hook de segurança padrão
# (protege contra commit de secrets)

Estrutura do CLAUDE.md Padrão

# CLAUDE.md — <nome do projeto>

## Regras do Projeto

### Padrão de Código
- <padrões específicos do projeto>

### Estrutura
- <árvore de diretórios>

### Workflows
- <como fazer build, test, deploy>

Read the full file on GitHub · 146 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. 9d ago First seen · 146 lines · 30 tokens per session scan D 1356c58d3f7c

Subscribe to this mod's changes

repo-onboard is an agent published in the GitHub repository zapprosite/claude-code-minimax (2 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 898 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.