stevengonsalvez/ainb-fleet:broadcast
plugins/ainb-fleet/skills/broadcast/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add stevengonsalvez/agents-in-a-box ainb-fleet:broadcastInstall 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 30, 2026, 4:51 AM24.2s1 file scanned
SKILL.md
- name:
- ainb-fleet:broadcast
- description:
- |
- Routing:
- peers-first (broker HTTP) when peer registered, tmux send-keys
- version:
- 0.1.0
- user-invocable:
- true
- - ainb-fleet:
- broadcast
ainb fleet:broadcast
Send one prompt to selected sessions. Mandatory targeting flag.
Run
ainb fleet broadcast "<prompt>" --all # every running session
ainb fleet broadcast "<prompt>" --filter "<regex>" # match tmux/workspace name
ainb fleet broadcast "<prompt>" --cwd "<substring>" # match cwd
Targeting flags (one required)
| flag | matches against |
|---|---|
| --all | every session in ainb fleet standup |
| --filter <regex> | regex against tmux_session OR workspace_name |
| --cwd <substring> | substring against cwd |
If none provided, the command exits with broadcast requires --all, --filter <regex>, or --cwd <substring> — by design, to prevent
accidental fan-out.
Output
ainb fleet broadcast — sent to N target(s)
✓ <name> via broker peer <peer_id>
✓ <name> via tmux <tmux_session>
✗ <name>: <reason>
✓ via broker = sent through claude-peers HTTP (clean, structured).
✓ via tmux = sent via tmux send-keys -l (literal mode, works for any
tmux pane regardless of peer state).
Routing rule
For each target:
- If session has
peer_idand broker is healthy → POST/send-messageto broker. - Else if session has
tmux_sessionand tmux says it exists →tmux send-keys -l. - Else →
Failed { reason: "no peer registered and no tmux session found" }.
Common flows
Cycle a specific app:
ainb fleet broadcast "/clear" --filter "shotclubhouse"
Pull latest in every active worktree:
ainb fleet broadcast "git pull" --cwd "/agents-in-a-box/worktrees/"
Universal reset:
ainb fleet broadcast "/exit" --all # careful — quits everything
Safety notes
tmux send-keys -luses literal mode → shell metacharacters in the prompt are safe (no injection).- Multi-line prompts: newlines in the broadcast text get sent as literal characters; the receiving claude reads them as a single message.
- The Enter key is sent after the literal text → claude sees the prompt as a submitted user message.
Verify a broadcast landed
For each target, tail the JSONL transcript:
ls -t ~/.claude/projects/<cwd-slug>/*.jsonl | head -1 | xargs grep "<prompt-text>"
(<cwd-slug> = replace / with - in the target's cwd.)
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