Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/stevengonsalvez/agents-in-a-boxnpx agentmods add skills/stevengonsalvez/agents-in-a-box/daemonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/daemon)<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/daemon"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/daemon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/daemon"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/daemon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 64 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 140 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.01443 |
| Opus 5 | $0.00044 | $0.00722 |
| Sonnet 5 | $0.00018 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
ainb-fleet:daemon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ainb fleet:daemon
DEPRECATED. Use
/ainb-fleet:atcinlitemode.ainb fleet atc mode <name> --set litegives you this exact loop — the same 5-second scan, the same auto-continueon the same known transient errors — owned by the ATC supervisor, inside its per-session retry cap and its safety ledger, and structurally unable to run beside the LLM heartbeat.This standalone daemon REFUSES to start while ATC owns the fleet in EITHER mode, because both send the same auto-
continueto the same pane and each de-dups only inside its own process, so the pane gets it twice. Pass--force-raceto run both anyway.The difference that matters is the retry cap: ATC gives up on a session after a bounded number of attempts and escalates to you. This daemon has no cap, so a session that keeps failing is retried forever, and running it beside ATC makes ATC's cap meaningless.
Kept for unmanaged one-off recovery, not removed.
Superseded by
/ainb-fleet:atcfor managed fleets. ATC absorbs this daemon's job — its ERR playbook does the same auto-continue, but with a per-session retry cap + escalate-on-exhaustion that this daemon lacks (see the sharp edge below). Preferainb fleet atc setup <name>for unattended supervision. The daemon stays for unmanaged one-off recovery; do not run it against sessions an ATC instance already manages — they race.
Background watcher. Reads each session's tmux pane (capture-pane) and
auto-continues sessions hitting API errors via tmux send-keys. It does
not register as a peer — it is purely tmux-driven (broker health is
checked only to print an informational line).
Run
ainb fleet daemon # quiet
ainb fleet daemon --verbose # log every detection + send
For real background use:
nohup ainb fleet daemon --verbose > ~/.ainb-fleet.log 2>&1 &
What it does each tick (every 5s)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed · +6 lines 45791c39dfa4
- 11d ago First seen · 149 lines · 89 tokens per session scan A 0516ca5524d3
ainb-fleet:daemon is a skill published in the GitHub repository stevengonsalvez/agents-in-a-box (23 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 1,443 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
A step-by-step debugging guide for finding the underlying cause of software problems before changing code.
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
parallel-debugging
Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.
error-handling-patterns
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.