Daemon Init logo

Daemon Init

Community
jmagly
daemon-init

Initialize AIWG daemon mode configuration from a named profile for persistent background sessions

Overview

Publisherjmagly
Repositoryaiwg
Skill namedaemon-init
Stars
225
Forks
34
Bundled files
Instructions only
LicenseMIT
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 jmagly on GitHub. Read the source before you install it.

Installation

Install the Daemon Init 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.
    https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/aiwg-utils/skills/daemon-init
  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/jmagly/aiwg.git /tmp/aiwg
mkdir -p .claude/skills
cp -r /tmp/aiwg/agentic/code/addons/aiwg-utils/skills/daemon-init .claude/skills/daemon-init
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Daemon Init 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 Daemon Init 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 Daemon Init 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.

Daemon Init

You initialize AIWG daemon mode configuration from a named profile. The daemon is a persistent AI session that handles background task execution, messaging integration, and multi-loop orchestration — running continuously rather than responding to individual prompts.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

  • "start daemon mode" → init with default profile
  • "set up background agent" → init with manager profile
  • "configure aiwg for continuous operation" → init with orchestrator profile
  • "i want aiwg running in the background" → init with manager profile
  • "reinitialize daemon" → init with --force

Trigger Patterns Reference

PatternExampleAction
Default init"initialize daemon"Run aiwg daemon-init
Named profile"init daemon as orchestrator"Run aiwg daemon-init orchestrator
Force reinit"reinitialize daemon config"Run aiwg daemon-init --force
Worker mode"set up a worker daemon"Run aiwg daemon-init worker
Monitor mode"run daemon in monitoring mode"Run aiwg daemon-init monitor

Behavior

When triggered:

  1. Extract intent:

    • Is a profile name specified? Default to manager if not.
    • Is --force needed (user mentioned reinitializing or overwriting)?
  2. Select the appropriate profile:

    ProfileAuthorityUse Case
    manager (default)Balanced — orchestrate and executeGeneral-purpose persistent agent
    orchestratorHigh — coordinate other agentsDriving multi-agent workflows
    workerLow — execute, minimal decisionsBackground task execution
    monitorRead-only — observe and alertOps monitoring, health checks
  3. Run the command:

    bash
    # Default profile (manager)
    aiwg daemon-init
    
    # Named profile
    aiwg daemon-init orchestrator
    aiwg daemon-init worker
    aiwg daemon-init monitor
    
    # Overwrite existing config
    aiwg daemon-init --force
    aiwg daemon-init orchestrator --force
  4. Know where config is written: .aiwg/daemon/config.yaml in the current project. This file controls:

    • Session persistence behavior
    • Messaging integration endpoints (Telegram, Slack, etc.)
    • Task queue and loop settings
    • Authority level and decision boundaries
  5. Report the result — Confirm which profile was initialized and the config path. If daemon is already initialized, remind the user to use --force to overwrite.

Examples

Example 1: Default initialization

User: "Set up daemon mode"

Extraction: Init request, no profile specified — use manager

Action:

bash
aiwg daemon-init

Response: "Daemon initialized with manager profile. Config written to .aiwg/daemon/config.yaml. To start the daemon, see docs/daemon-guide.md for session launch instructions."


Example 2: Orchestrator profile

User: "Initialize the daemon as an orchestrator — I want it coordinating multiple sub-agents"

Extraction: Init with orchestrator profile

Action:

bash
aiwg daemon-init orchestrator

Response: "Daemon initialized with orchestrator profile. High-authority orchestration settings applied. Config at .aiwg/daemon/config.yaml. The orchestrator profile enables aiwg mc (Mission Control) dispatch patterns."


Example 3: Force reinitialize

User: "Reinitialize the daemon — the old config is stale"

Extraction: Force reinit, no profile specified — use manager with --force

Action:

bash
aiwg daemon-init --force

Response: "Daemon config overwritten with manager profile. Previous config backed up to .aiwg/daemon/config.yaml.bak."


Example 4: Worker for CI pipeline

User: "I need a worker daemon for running background test loops in CI"

Extraction: Init with worker profile

Action:

bash
aiwg daemon-init worker

Response: "Daemon initialized with worker profile. Minimal decision authority configured — this profile executes tasks and reports results without autonomous orchestration. Suitable for CI background loops."

Clarification Prompts

If the user's intent is ambiguous:

  • "Which daemon profile should I use? Options: manager (default), orchestrator, worker, monitor"
  • "A daemon config already exists at .aiwg/daemon/config.yaml. Should I overwrite it with --force?"
  • "Are you initializing for a new project, or reconfiguring an existing daemon?"

References

  • @$AIWG_ROOT/src/cli/handlers/daemon.ts — Daemon command handler
  • @$AIWG_ROOT/docs/daemon-guide.md — Full daemon documentation including session launch
  • @$AIWG_ROOT/docs/messaging-guide.md — Messaging integration (Telegram, Slack) configuration
  • @$AIWG_ROOT/docs/cli-reference.md — CLI reference

Frequently asked questions

What does the Daemon Init AI skill do?

Initialize AIWG daemon mode configuration from a named profile for persistent background sessions

Why use Daemon Init on TypingMind?

Because you install it once and use it with any model. Daemon Init 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 Daemon Init in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/aiwg-utils/skills/daemon-init. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Daemon Init?

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 Daemon Init?

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

Is the Daemon Init AI skill free?

Yes. It is published on GitHub by jmagly under the MIT license. 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 👇