Skip to content
Agentmart
Submit a tool

fleet-liaison

Interact with the fleet liaison agent — check status, read batched messages, escalate outbound, pause/resume monitoring

Skill by supportersimulator

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying fleet-liaison?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/supportersimulator-fleet-liaison

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Interact with the fleet liaison agent — check status, read batched messages, escalate outbound, pause/resume monitoring

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/fleet-liaison

What's inside

Skill name
fleet-liaison
Description
Interact with the fleet liaison agent — check status, read batched messages, escalate outbound, pause/resume monitoring
License
MIT
Instructions
172 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Fleet Liaison

Interface for the coding agent to interact with the background fleet liaison. The liaison handles all fleet communication so you stay focused on code.

## Commands

### `/fleet-liaison status`

Show liaison state: pending message counts, active rebuttals, uptime.

```bash
# Read liaison state
cat /tmp/fleet-liaison-state.json 2>/dev/null | python3 -c "
import sys, json
try:
    s = json.load(sys.stdin)
    p = s.get('stats', {})
    print(f'Liaison: {\"PAUSED\" if s.get(\"paused\") else \"ACTIVE\"}')
    print(f'Last poll: {s.get(\"last_poll\", \"never\")}')
    print(f'Pending: {p.get(\"info\",0)} info, {p.get(\"urgent\",0)} urgent, {p.get(\"critical\",0)} critical')
    print(f'Total received: {p.get(\"received\",0)} | Sent: {p.get(\"sent\",0)} | Malformed: {p.get(\"malformed\",0)}')
    rb = s.get('active_rebuttals', [])
    if rb:
        print(f'Active rebuttals: {len(rb)}')
        for r in rb:
            print(f'  - {r.get(\"task_id\",\"?\")} phase={r.get(\"phase\",\"?\")}')
except Exception:
    print('Liaison not running or state file missing')
"

# Read batch summary
cat /tmp/fleet-liaison-batch.json 2>/dev/null | python3 -c "
import sys, json
try:
    b = json.load(sys.stdin)
    p = b.get('pending', {})
    print(f'Batch updated: {b.get(\"updated\",\"?\")}')
    print(f'Queued: {p.get(\"info\",0)} info, {p.get(\"urgent\",0)} urgent, {p.get(\"critical\",0)} critical')
except Exception:
    print('No batch file')
"
```

### `/fleet-liaison read`

Get and clear all batched messages. Returns the full batch JSON, then resets the batch file.

```bash
# Read batch
BATCH=$(cat /tmp/fleet-liaison-batch.json 2>/dev/null)
if [ -n "$BATCH" ]; then
    echo "$BATCH" | python3 -c "
import sys, json
b = json.load(sys.stdin)
items = b.get('items', [])
if not items:
    print('No pending messages')
else:
    for i in items:
        level = i.get('level','?')
        marker = {'CRITICAL':'!!!','URGENT':'!!','INFO':'.'}
        print(f'[{marker.get(level,\"?\")}] [{level}] {i.get(\"from\",\"?\")} | {i.get(\"type\",\"?\")} | {i.get(\"subject\",\"\")}')
        if i.get('summary'):
            print(f'    {i[\"summary\"]}')
"
    # Clear batch after reading
    echo '{"updated":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","pending":{"info":0,"urgent":0,"critical":0},"items":[]}' > /tmp/fleet-liaison-batch.json
else
    echo "No batch file — liaison may not be running"
fi
```

### `/fleet-liaison escalate <message>`

Send a structured packet through the liaison to a fleet peer. The liaison handles channel selection and delivery.

```bash
# Write to outbox for liaison to pick up and deliver
cat > /tmp/fleet-outbox-${MULTIFLEET_NODE_ID:-$(hostname -s)}/liaison-$(date +%s).json << 'MSG'
{
  "protocol": "3s-lan/v1",
  "message_type": "<type>",
  "from": "${MULTIFLEET_NODE_ID}",
  "to": "<target>",
  "task_id": null,
  "timestamp": "<ISO8601>",
  "payload": {
    "subject": "<subject>",
    "body": "<body>"
  }
}
MSG
```

Or send directly via daemon if available:

```bash
curl -sf -X POST http://127.0.0.1:8855/message \
  -H "Content-Type: application/json" \
  -d '{
    "type": "<message_type>",
    "from": "'${MULTIFLEET_NODE_ID:-$(hostname -s)}'",
    "to": "<target>",
    "payload": {
      "subject": "<subject>",
      "body": "<body>"
    }
  }'
```

### `/fleet-liaison pause`

Temporarily pause fleet monitoring. Liaison stops polling but retains state.

```bash
# Set paused flag
python3 -c "
import json, os
path = '/tmp/fleet-liaison-state.json'

From supportersimulator/multi-fleet, MIT.

More from supportersimulator/multi-fleet

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Apr 6, 2026 (7 months ago)
Last release
Apr 18, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from supportersimulator

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get fleet-liaison running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying fleet-liaison?

CallGet help
Cite this page

fleet-liaison skill. Agent Mart. https://agentmart.dev/skills/supportersimulator-fleet-liaison (last updated 2026-10-24)