daemon-status
Show daemon health, active sessions, task queue, and subsystem status
Best use case
daemon-status is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Show daemon health, active sessions, task queue, and subsystem status
Teams using daemon-status should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/daemon-status/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How daemon-status Compares
| Feature / Agent | daemon-status | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Show daemon health, active sessions, task queue, and subsystem status
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
SKILL.md Source
# Daemon Status Skill You detect when users want to check the AIWG daemon's health and operational status, then gather and present the information. ## Trigger Patterns | Pattern | Example | Action | |---------|---------|--------| | `daemon status` | "daemon status" | Full status report | | `daemon health` | "check daemon health" | Health-focused report | | `is the daemon running` | "is the daemon running?" | Quick running/stopped check | | `what's the daemon doing` | "what's the daemon doing right now?" | Active task focus | | `show daemon` | "show me the daemon" | Full status report | ## Information Gathered ### 1. Process Status ```bash # Check if daemon is running cat .aiwg/daemon/daemon.pid 2>/dev/null ps -p $(cat .aiwg/daemon/daemon.pid) 2>/dev/null ``` Report: running/stopped, PID, uptime ### 2. Active Sessions ```bash # Check active agent sessions ls .aiwg/daemon/sessions/ 2>/dev/null ``` Report: count, age, task descriptions ### 3. Task Queue ```bash # Check queued tasks cat .aiwg/daemon/queue.json 2>/dev/null ``` Report: pending count, active count, completed (last hour) ### 4. Subsystem Health | Subsystem | Check | Status | |-----------|-------|--------| | File watcher | `.aiwg/daemon/watcher.pid` | running/stopped | | Scheduler | `.aiwg/daemon/scheduler.pid` | running/stopped | | IPC socket | `.aiwg/daemon/aiwg.sock` | listening/down | | Messaging | `.aiwg/daemon/adapters/` | connected/disconnected | ### 5. Recent Activity ```bash # Last 5 completed tasks tail -5 .aiwg/daemon/activity.log 2>/dev/null ``` ## Output Format ``` Daemon Status ───────────────────────────────────── Status: Running (PID 12345, uptime 2h 15m) Sessions: 1 active, 0 queued Tasks: 3 completed (last hour), 1 active Subsystems: File watcher: running Scheduler: running (next: health-check in 12m) IPC socket: listening Messaging: Slack (connected), Discord (disconnected) Active Task: "Fix auth timeout in user service" — cycle 3/6, started 8m ago Recent: 14:32 Completed: "Update README badges" 14:15 Completed: "Run lint cleanup" 13:50 Completed: "Sync issue #42" ───────────────────────────────────── ``` ## Fallback When Daemon Not Running ``` Daemon is not running. Start it with: aiwg daemon start Last run: 2026-03-25 (2 days ago) Last shutdown: clean (SIGTERM) ``` ## References - @$AIWG_ROOT/docs/daemon-guide.md — Daemon architecture and operations - @$AIWG_ROOT/tools/daemon/daemon-main.mjs — Daemon implementation - @$AIWG_ROOT/tools/ralph-external/daemon-supervisor.mjs — Agent supervisor
Related Skills
customize-status
Show current AIWG customization status — mode, source path, what you've customized vs upstream
soul-status
Show SOUL.md enforcement state across all installed providers with quality check
rlm-status
Show status of RLM task tree execution
research-status
Show research corpus health and statistics
ralph-status
Check status of current or previous agent loop
project-status
Analyze project state from .aiwg/ artifacts and provide contextual status with recommended next steps
plugin-status
List installed Claude Code plugins with version, install date, and enabled status
pipeline-status
Show status overview of all LLM inference pipelines in the current project
marketing-status
Project directory path (default current directory)
hook-status
Show AIWG hook state across all installed providers
forensics-status
Show investigation status dashboard
daemon-init
Initialize AIWG daemon mode configuration from a named profile for persistent background sessions