# Deploy Rollback

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-entityprocess-agentv-deploy-rollback`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [EntityProcess](https://agentstack.voostack.com/s/entityprocess)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [EntityProcess](https://github.com/EntityProcess)
- **Source:** https://github.com/EntityProcess/agentv/tree/main/evals/agentic-engineering/workspace-template/plugins/deploy-auto/skills/deploy-rollback
- **Website:** https://agentv.dev

## Install

```sh
agentstack add skill-entityprocess-agentv-deploy-rollback
```

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

## About

# Deploy Rollback Skill

## Purpose

Rollback a failed or unwanted deployment. Reads `{output_dir}/deploy-plan.md` and reverses each completed step in reverse dependency order.

## Process

1. Read deploy-plan.md to identify completed steps
2. For each completed step (in reverse order):
   a. Execute the rollback command
   b. Verify the service returns to its previous state
   c. Run health checks
3. Write `{output_dir}/rollback-report.md`

## Stop Conditions

Stop and report immediately if:
- A rollback command fails
- Health checks fail after rollback
- The deploy plan cannot be read

## Source & license

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

- **Author:** [EntityProcess](https://github.com/EntityProcess)
- **Source:** [EntityProcess/agentv](https://github.com/EntityProcess/agentv)
- **License:** MIT
- **Homepage:** https://agentv.dev

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-entityprocess-agentv-deploy-rollback
- Seller: https://agentstack.voostack.com/s/entityprocess
- 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%.