# Ask Devin

> Asks Devin for Terminal for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.

- **Type:** Skill
- **Install:** `agentstack add skill-nix-tkobayashi-ask-devin-ask-devin`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [nix-tkobayashi](https://agentstack.voostack.com/s/nix-tkobayashi)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [nix-tkobayashi](https://github.com/nix-tkobayashi)
- **Source:** https://github.com/nix-tkobayashi/ask-devin

## Install

```sh
agentstack add skill-nix-tkobayashi-ask-devin-ask-devin
```

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

## About

# Ask Devin

Executes Devin for Terminal to get coding assistance.

**Note:** This skill requires Devin for Terminal to be installed and available in your system's PATH.

## Quick start

Run a single query with `-p` (print/non-interactive mode):

```bash
devin -p "Your question or task here"
```

## Common options

| Option | Description |
|--------|-------------|
| `-p PROMPT` | Non-interactive mode (print response and exit) |
| `--model MODEL` | Specify model (e.g. `claude-sonnet-4`, `opus`) |
| `--permission-mode MODE` | `auto` (read-only auto-approve) or `dangerous` (all auto-approve) |
| `--prompt-file FILE` | Load prompt from a file |

> For all available options, run `devin --help`

## Examples

**Ask a coding question:**

```bash
devin -p "How do I implement a binary search in Python?"
```

**Use a specific model:**

```bash
devin --model claude-opus-4.6 -p "Write a function that validates email addresses"
```

**Analyze code with dangerous permission mode:**

```bash
devin --permission-mode dangerous -p "Add error handling to all API endpoints"
```

## Notes

- Use `-p` for non-interactive (one-shot) mode; omit it for interactive sessions
- Default permission mode is `auto` (auto-approves read-only tools)
- The command inherits the current working directory

## Source & license

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

- **Author:** [nix-tkobayashi](https://github.com/nix-tkobayashi)
- **Source:** [nix-tkobayashi/ask-devin](https://github.com/nix-tkobayashi/ask-devin)
- **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-nix-tkobayashi-ask-devin-ask-devin
- Seller: https://agentstack.voostack.com/s/nix-tkobayashi
- 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%.