Droid Cli logo

Droid Cli

Organization
Factory-AI
droid-cli

Background knowledge for droid-control workflows -- not invoked directly. Droid CLI target patterns, shortcuts, modes, and launch helpers.

Overview

PublisherFactory-AI
Repositoryfactory-plugins
Skill namedroid-cli
Stars
111
Forks
15
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Factory-AI on GitHub. Read the source before you install it.

Installation

Install the Droid Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Factory-AI/factory-plugins.git /tmp/factory-plugins
mkdir -p .claude/skills
cp -r /tmp/factory-plugins/plugins/droid-control/skills/droid-cli .claude/skills/droid-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Droid Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Droid Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Droid Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Droid CLI Target

The orchestrator routed you here. Layer these target-specific patterns on top of the driver skill you already loaded.

Droid-specific shortcuts, modes, and launch patterns.

Shortcuts

ActionKey chordResult
Toggle Spec modeshift tabtoggles Spec mode on/off
Cycle autonomyctrl lOff > Low > Med > High > Off
Cycle modelsctrl ncycles available models
Cycle reasoningtabHigh > none > Low > Medium > High
Cancel / close / stopescstops streaming, closes overlays
Clear inputctrl uclears current line
Toggle bash mode! on empty inputswitches prompt between > and $
Help / shortcuts?opens keybinding help
Multiline inputshift enterinserts newline without submitting

Dialogs

When a dialog shows Use up/down to navigate...: up/down moves the highlight, enter selects, esc closes.

Slash commands

CommandPurpose
/helpShow commands
/settingsOpen settings menu
/modelOpen model selector
/clear or /newStart a new session
/sessionsBrowse previous sessions
/statusShow current config
/costShow usage / cost
/compress [prompt]Summarize and move to fresh session

File mentions

Type @ to open file suggestions, filter by typing, tab to accept, esc to cancel:

bash
$TCTL -s demo type "review @"
$TCTL -s demo type "package.json"
$TCTL -s demo press tab

Visual cues

StateWhat to look for
Spec mode oninput border shows Spec
Bash mode onprompt is $
Idle / readyprompt is > with no spinner
Dialog openboxed menu + navigation hint
File suggestionsdropdown under input
ThinkingThinking... and stop hint

Launching Droid

How droid-dev works

droid-dev is a thin bash shim at ~/.local/bin/droid-dev. It runs bun against whichever checkout DROID_DEV_REPO_ROOT points to — it does NOT use a pre-compiled binary. This means:

  • No per-branch builds. One npm run setup (in any checkout) installs the shim. Switching branches is instant via --repo-root.
  • Prerequisite: The target worktree must have node_modules installed (npm install at the repo root). If missing, the bun launch fails.
  • tctl --repo-root sets DROID_DEV_REPO_ROOT automatically and pins the session to that worktree.
  • tctl --cwd is independent of --repo-root: run droid against one worktree's code while sitting in a different project directory (e.g., a scratch project with its own .factory/settings.json hooks). Defaults to --repo-root when unset.

droid-dev

droid-dev launches require --repo-root (or --env DROID_DEV_REPO_ROOT=...). tctl enforces this — launches without it will fail:

bash
# tuistory (default — virtual PTY)
$TCTL launch "droid-dev" -s demo --backend tuistory \
  --repo-root /path/to/worktree \
  --cols 120 --rows 36

# true-input (real terminal proof — headless Wayland compositor)
$TCTL launch "droid-dev" -s demo --backend true-input \
  --repo-root /path/to/worktree

Feature branch / worktree

For comparisons, launch separate sessions pointing at different worktrees:

bash
$TCTL launch "droid-dev" -s before --backend tuistory \
  --repo-root /path/to/baseline-worktree \
  --cols 120 --rows 36 --record /tmp/before.cast \
  --env FORCE_COLOR=3 --env COLORTERM=truecolor

$TCTL launch "droid-dev" -s after --backend tuistory \
  --repo-root /path/to/candidate-worktree \
  --cols 120 --rows 36 --record /tmp/after.cast \
  --env FORCE_COLOR=3 --env COLORTERM=truecolor

Comparison setup (before/after demos)

For before/after comparisons, you need two worktree paths — one for the baseline and one for the candidate.

  1. Find existing worktrees: git worktree list in any checkout. The main clone (often on dev or main) is a valid baseline.
  2. Create if needed: git worktree add /tmp/baseline-worktree dev (or the relevant base branch).
  3. Ensure node_modules: Run npm install in any worktree that lacks it. This is the only setup needed — no npm run setup or CLI build per branch.
  4. Launch with --repo-root: Each tctl launch pins to one worktree.

Environment safety

tctl's runner script launches droid-dev via bash -lc, which loads a clean login shell. Stale FACTORY_* env vars from parent processes are typically overridden by the runner. If you suspect env contamination, pass explicit overrides with --env.

Exec mode

Non-interactive single-shot execution:

bash
droid exec "analyze this file"
droid exec --auto medium "run the tests"

Logging

Enable debug logging by passing the log file path via --env:

bash
$TCTL launch "droid-dev" -s demo --backend tuistory \
  --repo-root /path/to/worktree \
  --env FACTORY_LOG_FILE=/tmp/droid-test.log
tail -f /tmp/droid-test.log

Frequently asked questions

What does the Droid Cli AI skill do?

Background knowledge for droid-control workflows -- not invoked directly. Droid CLI target patterns, shortcuts, modes, and launch helpers.

Why use Droid Cli on TypingMind?

Because you install it once and use it with any model. Droid Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Droid Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Factory-AI/factory-plugins/tree/master/plugins/droid-control/skills/droid-cli. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Droid Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Droid Cli?

As many as you like. As long as a model supports skills, you can use Droid Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Droid Cli AI skill free?

It is published on GitHub by Factory-AI. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇