# Run AI Apps with Inference CLI

Teams often need several hosted AI models, but switching APIs slows routine work. This skill guides Claude, Codex, and Claude Code through belt CLI workflows.

## Install

```bash
npx skillstore add halt-catch-fire/agent-tools
```

## Metadata

- Status: approved
- Slug: halt-catch-fire-agent-tools
- Skillstore revision: r1
- Version status: missing
- Tree hash: c26e5bcf1cd03855f9dcafe8a940603fd0fb2423559ffc394089238827785254
- Author: halt-catch-fire
- GitHub username: halt-catch-fire
- License: MIT
- Repository: https://github.com/halt-catch-fire/skills/tree/main/tools/agent-tools/
- Ref: a06681402992ceae98ba04d54cfd4ab004862696
- 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: network, env\_access, filesystem, external\_commands
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/halt-catch-fire-agent-tools
- Manifest: https://skillstore.pages.dev/api/skills/halt-catch-fire-agent-tools/manifest

## Capabilities

- Explains setup and authentication for the belt CLI.
- Discovers public and user apps with store, search, category, and detail commands.
- Runs inference.sh apps with inline input, saved input files, and version pins.
- Handles local file inputs for apps that accept uploads.
- Tracks long-running tasks and retrieves saved results.
- Lists related skills for images, video, LLMs, search, avatars, and Twitter automation.

## Use Cases

- Prototype Multimodal Workflows: Discover image, video, audio, search, and LLM apps, then compare inputs and outputs from one CLI flow.
- Automate Media Generation Tasks: Run hosted image, video, upscaling, avatar, and utility apps without managing local GPU infrastructure.
- Run Research Jobs from an Agent: Use search and LLM apps from an agent session, then track task status and retrieve result links.

## Prompt Templates

### Find an App

```
Use agent-tools to search the inference.sh app store for image generation apps. Show three options and the required inputs.
```

### Run a Simple Job

```
Use agent-tools to prepare a small text-to-image job with my prompt. Ask before submitting the remote job.
```

### Track a Long Job

```
Use agent-tools to submit a video generation job without waiting. Then show status checks and result retrieval steps.
```

### Build a Multistep Workflow

```
Use agent-tools to discover apps, generate sample inputs, run an image-to-video workflow, and summarize every remote action before execution.
```

## Limitations

- Requires a working belt CLI installation and an inference.sh account.
- Remote app behavior, pricing, availability, and outputs are controlled by inference.sh providers.
- Local file uploads can expose sensitive data if paths are selected incorrectly.
- Account-changing actions require user approval and valid credentials.

## Best Practices

- Ask for explicit approval before installing CLIs, uploading files, or posting to external services.
- Generate sample inputs before running unfamiliar apps.
- Pin app versions for repeatable workflows when available.

## Anti Patterns

- Do not pipe remote installers into a shell in unattended workflows.
- Do not upload broad directories or sensitive local files as app inputs.
- Do not use social media actions without user-reviewed text and account confirmation.

## Security Audit

- Audited at: 2026-07-06T16:30:57.742\+00:00
- Summary: The audit confirms critical risk from repeated remote installer commands that pipe fetched content into a shell. Most placeholder API key, documentation link, and benign path examples are false positives, but the skill also documents local file uploads and Twitter or X account actions that need explicit user control.

## Stats

- Views: 0
- Downloads: 6
- Favorites: 0
- Popularity score: 0