# Git Workflow

> Git Workflow skill.

- **Type:** Skill
- **Install:** `agentstack add skill-agent-kit-startup-agent-kit-git-workflow`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [agent-kit-startup](https://agentstack.voostack.com/s/agent-kit-startup)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [agent-kit-startup](https://github.com/agent-kit-startup)
- **Source:** https://github.com/agent-kit-startup/agent-kit/tree/main/registry/skills/core/git-workflow

## Install

```sh
agentstack add skill-agent-kit-startup-agent-kit-git-workflow
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Git Workflow

Two-step promote: **staging → production**. Never commit directly to `main`.

## Commands

| User says | Slash | Effect |
|-----------|-------|--------|
| `git staging` (legacy: `git homolog`) | `/git-staging` | Local → `staging` branch (legacy repos may use `homologacao`) |
| `git prod` | `/git-prod` | `staging` → `main` (explicit confirmation) |

Spec: `autogit/gitupdate.md` when present in the project.

## Agent memory loop

```
plan → /handoff → /git-staging → (approval) → /git-prod → memory-loop WRITE if needed
```

After each promote, update `.cursor/HANDOFF.md`. Conventional Commits. Prefer `/worktree` for risky experiments.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [agent-kit-startup](https://github.com/agent-kit-startup)
- **Source:** [agent-kit-startup/agent-kit](https://github.com/agent-kit-startup/agent-kit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-agent-kit-startup-agent-kit-git-workflow
- Seller: https://agentstack.voostack.com/s/agent-kit-startup
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.