ainb-fleet:daemon
Long-running watcher that scans every claude session every 5s and auto-sends `continue` to any session whose recent tmux pane buffer matches a known API-error regex (rate_limited, overloaded_error, internal_server_error, request_timeout, socket_hang_up, fetch_failed, ECONNRESET). Use this when you want unattended recovery from transient API failures across the fleet.
Best use case
ainb-fleet:daemon is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Long-running watcher that scans every claude session every 5s and auto-sends `continue` to any session whose recent tmux pane buffer matches a known API-error regex (rate_limited, overloaded_error, internal_server_error, request_timeout, socket_hang_up, fetch_failed, ECONNRESET). Use this when you want unattended recovery from transient API failures across the fleet.
Teams using ainb-fleet:daemon 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/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ainb-fleet:daemon Compares
| Feature / Agent | ainb-fleet:daemon | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Long-running watcher that scans every claude session every 5s and auto-sends `continue` to any session whose recent tmux pane buffer matches a known API-error regex (rate_limited, overloaded_error, internal_server_error, request_timeout, socket_hang_up, fetch_failed, ECONNRESET). Use this when you want unattended recovery from transient API failures across the fleet.
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.
SKILL.md Source
# ainb fleet:daemon Background watcher. Registers as peer `ainb-fleet-cp`. Auto-continues sessions hitting API errors. ## Run ```bash ainb fleet daemon # quiet ainb fleet daemon --verbose # log every detection + send ``` For real background use: ```bash nohup ainb fleet daemon --verbose > ~/.ainb-fleet.log 2>&1 & ``` ## What it does each tick (every 5s) 1. Re-discover all sessions (ainb + peers + jobs, merged + deduped). 2. For each tmux-bearing session: `tmux capture-pane -p -S -80` (last 80 lines). 3. Run the API-error regex set over the buffer. 4. If a match fires AND the (session_id, pattern, snippet-tail) dedupe key hasn't been seen yet → send `continue` to that session via the standard route (peers-first, tmux fallback). ## Detected error patterns | name | regex | |---|---| | `rate_limited` | `\brate[_ ]limited\b` | | `overloaded` | `\boverloaded_error\b \| \bModel is overloaded\b` | | `internal_server_error` | `\binternal_server_error\b` | | `request_timeout` | `\brequest timed out\b` | | `socket_hang_up` | `\bsocket hang up\b` | | `fetch_failed` | `\bAPI Error\b \| \bfetch failed\b` | | `connection_reset` | `\bECONNRESET\b \| \bconnection reset\b` | Case-insensitive. Word-boundaried to avoid false positives. ## Dedupe key ``` key = (session_id, pattern_name, last_40_chars_of_match_context) ``` Within a single daemon run, the same `key` only fires `continue` once. This prevents spam when the error text scrolls up but is still in the buffer. ## ⚠️ Sharp edge — no retry cap in v0.1 If a session is permanently broken (wrong credentials, model deprecated, loop bug), the daemon will keep firing `continue` forever as new errors match new dedupe keys. Watch the daemon log; kill it (`Ctrl-C` or `kill <pid>`) when you see runaway repetition. Roadmap: per-session retry cap with exponential backoff. ## Stop the daemon ```bash # foreground: Ctrl-C # background: pkill -INT -f "ainb fleet daemon" # or kill by exact PID if you know it kill <pid> ``` The daemon's SIGINT handler unregisters from the broker before exit, so peers won't see a stale `ainb-fleet-cp` entry. ## Observe what the daemon is doing With `--verbose`, every detection prints: ``` [fleet/daemon] broker healthy at 127.0.0.1:7899 [fleet/daemon] auto-continue -> <tmux_session> (<pattern>) ``` Tail the nohup log to watch in real time: ```bash tail -F ~/.ainb-fleet.log ``` ## When NOT to run the daemon - During hand-debugging — the daemon will send `continue` while you're reading the error, racing your investigation. - On a fleet doing batch work that explicitly throws errors as control flow — the daemon will misinterpret intentional errors. - When the broker is down AND every session is tmux-only — the daemon still works via tmux fallback but loses peer-aware routing.
Related Skills
test-ainb
Run tests for the ainb (agents-in-a-box) Rust workspace via a 5-layer strategy — unit, insta snapshot, mock-plugin compositing, real-plugin spawn, vhs recording. Wraps cargo + insta + vhs into one CLI. Use when Stevie says "/test-ainb", "test ainb", "run ainb tests", "snapshot <component>", "regenerate vhs tapes", or any phrasing about validating ainb test layers. The skill autodetects which ainb-tui worktree the cwd sits in and dispatches to scripts/run.sh.
ainb-fleet:standup
Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, see which sessions have a peer registered (broker-routable) vs tmux-only, check the `summary` of each session, or pipe the list into jq for filtering. Default output: text table. Pass --format json for LLM consumption.
ainb-fleet:sequence
Ordered multi-step prompts to fleet targets, ack-gated between steps via JSONL assistant-turn-end detection. Use for cycles like disconnect→reconnect→verify, or any flow where step N+1 requires step N to have completed first. The skill BLOCKS until each target's transcript shows the next assistant turn finishing OR per-step timeout fires (default 300s).
ainb-fleet:needs
Center control panel — enumerate every claude session that is blocked waiting on something: a user answer (AskUserQuestion fired), an API error retry, an idle assistant turn-end with no follow-up, or an explicit WAITING: marker. Returns rich JSON with signal kind + context per session. Use this when you've stepped away from the fleet and want one place to see everything that wants your attention and answer it.
ainb-fleet:fleet-needs
Workflow-backed Jarvis control panel. Runs the deterministic `hangar` workflow with verb=needs (discover → enrich → prioritize), renders the Jarvis HUD from its render-ready cards, fires AskUserQuestion per blocked session, and routes each answer back via tmux send-keys (broker fallback only). Requires the workflow gate (CLAUDE_CODE_WORKFLOWS=1). If the gate is off, fall back to the prompt-driven `/ainb-fleet:needs` skill.
ainb-fleet:broadcast
Fan out a single prompt to selected claude sessions across the fleet. Use when you need to apply the same instruction (e.g. `/clear`, `git pull`, `remote-control disconnect`) to many sessions at once. Routing: peers-first (broker HTTP) when peer registered, tmux send-keys fallback otherwise. Refuses to run without an explicit targeting flag (--all, --filter <regex>, or --cwd <substring>) — no implicit fan-out.
ainb-fleet
Fleet orchestration overview — the `ainb fleet ...` Rust subcommand namespace for driving every claude session on the host. Routes to one of five sub-skills (standup / broadcast / sequence / needs / daemon). Invoke this for an at-a-glance map of what fleet can do; reach for the specific sub-skill for the verb you want.
workflow
Guide through structured delivery workflow with plan, implement, validate phases
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
validate
Verify implementation against specifications
ui-ux-pro-max
UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, Astro, Nuxt, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
tui-style-guide
TUI style guide for consistent terminal interface design