adal-cli
The automation-first agent harness. Every coding agent can build — AdaL does GTM directly from your codebase.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/SylphAI-Inc/adal-cli with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/SylphAI-Inc/adal-cli'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/sylphai-inc--adal-cli)HTML
<a href="/listings/sylphai-inc--adal-cli"><img src="/api/listings/sylphai-inc--adal-cli/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
These steps run a script from the network that findsafeskills does not scan.
Native install is recommended: it manages AdaL's runtime and updates consistently across platforms.
**macOS, Linux, WSL:**
curl -fsSL https://adal.sylph.ai/install.sh | bash
**Windows PowerShell:**
irm https://adal.sylph.ai/install/windows | iex
**Windows CMD:**
powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://adal.sylph.ai/install/windows | iex"
> If `irm` is not recognized, you are in CMD rather than PowerShell — use the Windows CMD command above, or open PowerShell.
Then go to your working directory and run:
adal
First run opens the browser for authentication. See the [Quickstart](https://docs.sylph.ai/getting-started/quickstart) for details.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 212 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # AdaL CLI
- <div align="center">
- <img src="assets/adal-face-logo.png" alt="AdaL Face" width="150" />
-
- <img src="assets/adal-text-logo.png" alt="AdaL Text" width="280" />
- <br /><br />
- [](https://docs.sylph.ai)
- [](https://blog.sylph.ai)
- [](https://adalagent.ai/product/cli)
- [](https://github.com/SylphAI-Inc/skills)
- [](https://discord.com/invite/ezzszrRZvT)
- [](https://x.com/adalagent)
- <br />
- <a href="https://www.youtube.com/watch?v=szLnhpO9QE8">
- <img src="https://img.youtube.com/vi/szLnhpO9QE8/maxresdefault.jpg" alt="AdaL CLI Demo" width="600" />
- </a>
- <br />
- <a href="https://www.youtube.com/watch?v=szLnhpO9QE8">▶️ Watch the demo on YouTube</a>
- </div>
- ---
- ## About
- AdaL is an AI agent for video. You tell it what you need and it makes launch films, product demos, UGC ads, podcast clips and event recaps, ready to edit and ship. It runs as a desktop app and in your terminal, and is named after Ada Lovelace, the world's first programmer. Learn more at [adalagent.ai](https://adalagent.ai/).
- AdaL CLI is the terminal version. It orchestrates agents, models and tools into end-to-end workflows, so you can script video work from the command line and still use it for code, with Claude, GPT, Gemini, GLM, Kimi, DeepSeek, MiniMax and local models.
- **This repository is the community home for AdaL CLI** — report issues, share what you build, and contribute skills.
- ### Hackathon presentation
- Open the [`@skills:` system card](https://sylphai-inc.github.io/adal-cli/hackathon/) for a presentation-ready overview of reusable agent knowledge, skill delivery, and the two main workflows.
- Presenter notes and local preview instructions are in [`hackathon/README.md`](hackathon/README.md).
- ### Install AdaL CLI
- Native install is recommended: it manages AdaL's runtime and updates consistently across platforms.
- **macOS, Linux, WSL:**
- ```bash
- curl -fsSL https://adal.sylph.ai/install.sh | bash
- ```
- **Windows PowerShell:**
- ```powershell
- irm https://adal.sylph.ai/install/windows | iex
- ```
- **Windows CMD:**
- ```bat
- powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://adal.sylph.ai/install/windows | iex"
- ```
- > If `irm` is not recognized, you are in CMD rather than PowerShell — use the Windows CMD command above, or open PowerShell.
- Then go to your working directory and run:
- ```bash
- adal
- ```
- First run opens the browser for authentication. See the [Quickstart](https://docs.sylph.ai/getting-started/quickstart) for details.
- ## The CLI
- **Start where developers move fastest.** AdaL CLI brings agentic work into the terminal — with model switching, reviewable tool use, session memory, and IDE handoff.
- - **Terminal-native** — command discovery, tool confirmations, streaming work, and clean recovery paths.
- - **Review-first** — tool calls, file edits, diffs, and plans stay visible, so you understand the work before signing off.
- - **Model freedom** — switch between Claude, Gemini, GLM, Kimi, DeepSeek, MiniMax and more from a fast command palette.
- - **CLI → IDE handoff** — open the same session in AdaL's agentic IDE when a task needs files, terminal, and canvas together.
- | Command | What it does |
- |---|---|
- | `/model` | Choose the best model for the job |
- | `/ide` | Open the current session in the agentic IDE |
- | `/resume` | Return to previous work with context intact |
- | `/stats` | Inspect session health, model, and usage |
- More on the [CLI product page](https://adalagent.ai/product/cli).
- ## Documentation
- Everything is published at [docs.sylph.ai](https://docs.sylph.ai/).
- **Get started**
- | Page | What it covers |
- |---|---|
- | [Quickstart](https://docs.sylph.ai/getting-started/quickstart) | Install, authenticate, first run |
- | [Models & Billing](https://docs.sylph.ai/getting-started/models) | Supported models and pricing |
- | [Input Methods](https://docs.sylph.ai/getting-started/input-methods) | Files, images, pasted content |
- | [Workflows & Examples](https://docs.sylph.ai/getting-started/workflows-and-examples) | Real end-to-end usage |
- **Features**
- | Page | What it covers |
- |---|---|
- | [Slash Commands](https://docs.sylph.ai/features/slash-commands) · [Keyboard Shortcuts](https://docs.sylph.ai/features/keyboard-shortcuts) | Drive the CLI fast |
- | [Skills & Plugins](https://docs.sylph.ai/features/plugins-and-skills) | Extend the agent |
- | [MCP Servers](https://docs.sylph.ai/features/mcp-support-proposed) | Model Context Protocol |
- | [Deep Research](https://docs.sylph.ai/features/deep-research) · [Web Search](https://docs.sylph.ai/features/web-search) | Research from the terminal |
- | [Browser Use](https://docs.sylph.ai/features/browser-use) | Drive a real browser |
- | [Image Generation & Analysis](https://docs.sylph.ai/features/image-generation) | Create and read images |
- | [Headless Mode](https://docs.sylph.ai/features/headless-mode) · [Cron](https://docs.sylph.ai/features/cron-scheduled-prompts) | Scripting, CI, schedules |
- | [Local Models](https://docs.sylph.ai/features/local-models) · [BYOAK](https://docs.sylph.ai/features/bring-your-own-api-key) | Run local or bring your own keys |
- | [Manage & Resume Sessions](https://docs.sylph.ai/features/manage-conversations) | History, stats, resuming work |
- **Also:** [Changelog](https://docs.sylph.ai/changelog) · [Troubleshooting](https://docs.sylph.ai/troubleshooting/linux-clipboard)
- ## Blog
- Let's have a journey on agents and models — [blog.sylph.ai](https://blog.sylph.ai/).
- | Post | |
- |---|---|
- | [Loop Engineering For Everyone](https://blog.sylph.ai/posts/loop-engineering-for-everyone) | Making loop engineering simple and affordable enough for every engineer |
- | [True Autonomous Coding Agents Require Browser Use](https://blog.sylph.ai/posts/coding-agent-autonomous-browser-use) | Real production bugs live in cookies, hydration, redirects, and clicks |
- | [AdaL Is 100% Aligned with Andrej Karpathy](https://blog.sylph.ai/posts/karpathy-agentic-engineering-adal) | Human understanding is the bottleneck of agentic engineering |
- | [The Ultimate Guide to Agentic Tool Calling](https://blog.sylph.ai/posts/ultimate-guide-agentic-tool-calling) | What really happens between the model and the JSON tool call |
- | [The Last Harness You'll Ever Build](https://blog.sylph.ai/posts/last-harness-youll-ever-build) | The hard part is no longer the model — it is everything around it |
- ## 📝 Contributing
- Skills are the best way to contribute. A skill is a markdown file that teaches the agent a repeatable workflow — no need to touch the CLI internals.
- Skills live in [SylphAI-Inc/skills](https://github.com/SylphAI-Inc/skills) (MIT) and install straight into the CLI:
- ```bash
- /plugin marketplace add SylphAI-Inc/skills
- /plugin install core-skills@adal-agent-skills
- /skills # see what you have
- ```
- ### Contribute a Skill
- 1. **Fork** [SylphAI-Inc/skills](https://github.com/SylphAI-Inc/skills)
- 2. **Create** your skill at `skills/<your-skill-name>/SKILL.md`
- 3. **Register** it in `.claude-plugin/marketplace.json`
- 4. **Open a pull request**
- ```markdown
- ---
- name: skill-name
- description: Brief description for the skills list
- author: your-username
- version: 1.0.0
- ---
- # Skill Title
- ## When to Use
- Describe the trigger conditions.
- ## Instructions
- Step-by-step guidance for the agent.
- ```
- New to it? Install [create-skill](https://github.com/SylphAI-Inc/skills/blob/main/skills/create-skill/SKILL.md) and let AdaL scaffold one with you. For a larger example, see [swe-cli-skills](https://github.com/SylphAI-Inc/swe-cli-skills).
- ### Share Your Use Case
- The best way to share a workflow is to ship it as a skill — then anyone can install it in one command. If you have a process that works, package it up and send it over.
- **[Open a pull request →](https://github.com/SylphAI-Inc/skills/compare)**
- In the PR description, tell us:
- - What you were trying to do
- - How you used AdaL — prompts, skills, models, commands
- - What worked, and what didn't
- - Anything you would want next
- Screenshots and terminal recordings welcome. Prefer to chat first? Post in [Discord](https://discord.com/invite/ezzszrRZvT) or tag [@adalagent](https://x.com/adalagent) on X.
- ## 🐛 Reporting Issues
- **[Open an Issue →](https://github.com/SylphAI-Inc/adal-cli/issues/new)**
- Please include:
- - What you expected vs what happened
- - Steps to reproduce (if applicable)
- - AdaL CLI version (`adal -v`)
- - OS and terminal
- ## Links
- - **Docs:** [docs.sylph.ai](https://docs.sylph.ai)
- - **Blog:** [blog.sylph.ai](https://blog.sylph.ai/)
- - **CLI product page:** [adalagent.ai/product/cli](https://adalagent.ai/product/cli)
- - **Company:** [adalagent.ai/company](https://adalagent.ai/company)
- - **Skills marketplace:** [github.com/SylphAI-Inc/skills](https://github.com/SylphAI-Inc/skills)
- - **Discord:** [Join our community](https://discord.com/invite/ezzszrRZvT)
- - **X (Twitter):** [@adalagent](https://x.com/adalagent)
- - **SylphAI:** [adalagent.ai](https://adalagent.ai/)
- ---
- <div align="center">
- Built by AdaL & <a href="https://adalagent.ai/">SylphAI</a>
- </div>
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.