# Spawn Coding Agents in New Terminals

Starting separate AI coding sessions across different CLIs requires platform-specific commands. This skill launches supported agents in new terminals and can capture their output.

## Install

```bash
npx skillstore add consiliency/spawn-agent
```

## Metadata

- Status: approved
- Slug: consiliency-spawn-agent
- Skillstore revision: r2
- Version status: missing
- Tree hash: 244de760d0ffa39e873983b2f9bd45cbfe5e5a59e36f1f25b5e771ba00b1c9a7
- Author: Consiliency
- GitHub username: Consiliency
- License: MIT
- Repository: https://github.com/Consiliency/treesitter-chunker/tree/main/.ai-dev-kit/skills/spawn/agent
- Ref: c43861a65bb95efcae259cd161c9d6f4dc7eec6f
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: blocked
- Manual install advisory: allowed\_with\_warning
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: env\_access, external\_commands, filesystem
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/consiliency-spawn-agent
- Manifest: https://skillstore.pages.dev/api/skills/consiliency-spawn-agent/manifest

## Capabilities

- Selects Claude Code, Codex, Gemini, Cursor, OpenCode, or Copilot from the user request.
- Uses Claude Code when the user does not specify an agent.
- Opens separate terminal sessions on macOS, Windows, WSL, and Linux.
- Supports interactive sessions, captured output, and full debug logging.
- Detects common authentication failures and can open provider login sessions.
- Waits for a forked process marker and returns saved output with a timeout.

## Use Cases

- Delegate a Focused Coding Task: Open a separate agent session to investigate a test failure while the main session continues.
- Compare Provider Recommendations: Launch different coding agents with the same design question and compare their findings.
- Capture an Automated Review: Run a non-interactive review and retrieve the saved response for a later workflow step.

## Prompt Templates

### Open a Basic Review Session

```
Spawn Claude Code in a new terminal. Ask it to review the current changes and summarize possible defects.
```

### Investigate a Failing Test

```
Spawn Codex in a new terminal. Ask it to diagnose failures in [test path] and propose a focused fix.
```

### Continue with Conversation Context

```
Spawn Gemini with a summary of our conversation. Ask it to evaluate [design decision] and list tradeoffs without editing files.
```

### Capture a Constrained Analysis

```
Spawn Cursor in non-interactive mode with output capture. Limit its scope to [directory] and permit only [approved commands].
```

## Limitations

- The selected provider CLI must be installed and authenticated.
- Terminal behavior depends on AppleScript, Windows Terminal, WSL, tmux, or a local shell.
- Commands are not isolated safely and may run with broad local permissions.
- Output capture and completion tracking are less reliable on Windows.

## Best Practices

- Review the generated command, working directory, and permission mode before launching an agent.
- Use sandboxed, approval-based execution and grant only the tools required for the task.
- Remove secrets from conversation summaries and delete captured output after use.

## Anti Patterns

- Do not place API keys, tokens, or passwords in prompts or command-line arguments.
- Do not disable sandbox and approval controls for routine tasks.
- Do not treat a successful spawn as proof that the delegated task completed correctly.

## Security Audit

- Audited at: 2026-07-23T12:34:24.033\+00:00
- Summary: The skill intentionally launches external CLI agents, and fork\_terminal.py inserts command strings into platform shells without safe argument boundaries. Many documentation and keyword findings are false positives, but insecure temporary files and instructions to disable approval controls are confirmed. Publication should require safer defaults and hardened command and file handling.

## Stats

- Views: 229
- Downloads: 10
- Favorites: 0
- Popularity score: 0