stevengonsalvez/ainb-fleet
plugins/ainb-fleet/skills/ainb-fleet/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add stevengonsalvez/agents-in-a-box ainb-fleetInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 29, 2026, 4:48 AM168.3s1 file scanned
SKILL.md
- name:
- ainb-fleet
- description:
- |
- version:
- 0.1.0
- user-invocable:
- true
ainb fleet — overview
Single Rust binary (ainb) provides 5 orchestration verbs across every
claude session running on this host. Each verb has its own colon-namespaced
sub-skill with focused docs.
Verbs
| sub-skill | what it does |
|---|---|
| /ainb-fleet:standup | List every claude session — merged across ainb · peers · bg jobs |
| /ainb-fleet:broadcast | Send one prompt to selected sessions |
| /ainb-fleet:sequence | Ordered multi-step prompts, ack-gated between steps |
| /ainb-fleet:needs | Show sessions blocked on input / errors / waiting |
| /ainb-fleet:daemon | Background watcher that auto-continues API errors |
Architecture (1-line)
discover (ainb + peers + jobs) ──▶ state read ──▶ send (peers-first, tmux fallback)
Global flag
--format json|text|csv|markdown (default text). Prefer --format json
when an LLM is the consumer.
Discovery sources
- ainb — every session ainb has spawned via
ainb run - peers — sessions registered with the claude-peers broker (
~/.claude-peers.db) - jobs — bg-session dirs under
~/.claude/jobs/
Merged + deduped by cwd so the same session in two sources collapses
into one record with sources: ["ainb", "peers"].
Environment overrides
| var | default | use |
|---|---|---|
| AINB_BIN | ainb | override binary the discover layer shells to (tests) |
| AINB_FLEET_PEER_ID | ainb-fleet-cp | peer id the daemon registers as |
| AINB_FLEET_JOBS_DIR | ~/.claude/jobs | bg-job scan root |
| CLAUDE_PEERS_DB | ~/.claude-peers.db | broker sqlite path |
| CLAUDE_PEERS_PORT | 7899 | broker HTTP port |
See also
ainb list— lifecycle-only session list (no peer/jobs enrichment)ainb attach <workspace>— drop into a session's tmuxainb kill <workspace>— terminate a single session by exact name
Related Skills
stevengonsalvez/reflect:cost
documentation
VerifiedTrustedCommunity
Report reflect drain spend over a time window — tokens split by cached (cache_read), uncached writes (cache_creation), and io (input+output), with a $ estimate, grouped by day / outcome / model / transcript. Reads the drainer's cost log and surfaces outlier runs and cache-reuse health (the 41.5M-token failure mode = low cache reuse + high cache writes). Use to answer "what is reflection costing me" for the last day / week.
12SKILL.mdUpdated Jun 2, 2026
stevengonsalvez/ainb-fleet:standup
development
VerifiedTrustedCommunity
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.
10SKILL.mdUpdated May 31, 2026
stevengonsalvez/ainb-fleet:sequence
testing
VerifiedTrustedCommunity
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).
10SKILL.mdUpdated May 31, 2026
stevengonsalvez/ainb-fleet:needs
development
VerifiedTrustedCommunity
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.
10SKILL.mdUpdated May 31, 2026