Skip to content
Deployment
Skill

/update-team

Update agent team services with latest configuration from setup-agent-team and restart them

From plugin
spawn
2217 skills
Install
$ npx -y skills add OpenRouterLabs/spawn --skill update-team --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/update-team

Context preview

The summary Claude sees to decide when to auto-load this skill.

Update agent team services with latest configuration from setup-agent-team and restart them

SKILL.md

update-team.SKILL.md
name: update-team
description: Update agent team services with latest configuration from setup-agent-team and restart them
argument-hint: "[service-name] [--check-only]"
allowed-tools: Bash, Read, Edit, Glob, Grep

Update Agent Team Services

Update the trigger server and wrapper scripts with the latest configuration from `.claude/skills/setup-agent-team/SKILL.md`, then restart the services to apply changes.

Arguments

  • `service-name` (optional) — Update only this service (e.g., `discovery`, `refactor`, `security`, `qa`). If omitted, updates all services.
  • `--check-only` — Show what would be updated without making changes or restarting services.

**$ARGUMENTS**

Overview

This skill: 1. Reads the latest setup-agent-team SKILL.md for current best practices 2. Identifies all deployed services by scanning for `start-*.sh` wrappers 3. Updates wrapper scripts with correct env vars and paths 4. Restarts systemd services to apply changes 5. Verifies services are running and healthy

Step 1: Determine repository path

Detect the current repository path:

REPO_ROOT="$(cd /root/spawn 2>/dev/null && pwd || cd /home/sprite/spawn 2>/dev/null && pwd)"
echo "Repository root: $REPO_ROOT"

Determine home directory:

if [[ "$REPO_ROOT" == "/root/spawn" ]]; then
    HOME_DIR="/root"
    SERVICE_USER="root"
    SERVICE_GROUP="root"
elif [[ "$REPO_ROOT" == "/home/sprite/spawn" ]]; then
    HOME_DIR="/home/sprite"
    SERVICE_USER="sprite"
    SERVICE_GROUP="sprite"
else
    echo "ERROR: Unknown repository path: $REPO_ROOT"
    exit 1
fi

echo "Home directory: $HOME_DIR"
echo "Service user/group: $SERVICE_USER/$SERVICE_GROUP"

Step 2: Read latest setup-agent-team instructions

Read the SKILL.md to check for:

  • Latest env var requirements
  • Recommended timeout values
  • New mandatory settings
  • Path patterns
cat "$REPO_ROOT/.claude/skills/setup-agent-team/SKILL.md"

Key things to extract from SKILL.md:

  • Required env vars: `TRIGGER_SECRET`, `TARGET_SCRIPT`, `REPO_ROOT`, `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS`, `MAX_CONCURRENT`, `RUN_TIMEOUT_MS`
  • Recommended `RUN_TIMEOUT_MS` values per service
  • Path templates for systemd service files

Step 3: Identify deployed services

Find all wrapper scripts:

ls -1 "$REPO_ROOT/.claude/skills/setup-agent-team/start-"*.sh 2>/dev/null | while read -r wrapper; do
    basename "$wrapper" | sed 's/^start-//;s/\.sh$//'
done

For each service found, check if it has a corresponding systemd unit:

systemctl list-units --all --type=service --plain --no-legend | grep -E 'discovery-trigger|refactor|spawn-security|spawn-qa' | awk '{print $1}'

Match wrappers to systemd units:

  • `start-discovery.sh` → `discovery-trigger.service`
  • `start-refactor.sh` → `refactor.service`
  • `start-security.sh` → `spawn-security.service`
  • `start-qa.sh` → `spawn-qa.service` (if exists)

Step 4: Check wrapper script compliance

For each wrapper script, verify it has:

Required env vars

# Check if wrapper has all required env vars
grep -q 'export TRIGGER_SECRET=' "$wrapper_path" || echo "MISSING: TRIGGER_SECRET"
grep -q 'export TARGET_SCRIPT=' "$wrapper_path" || echo "MISSING: TARGET_SCRIPT"
grep -q 'export REPO_ROOT=' "$wrapper_path" || echo "MISSING: REPO_ROOT"
grep -q 'export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1' "$wrapper_path" || echo "MISSING: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS"
grep -q 'export MAX_CONCURRENT=' "$wrapper_path" || echo "MISSING: MAX_CONCURRENT"
grep -q 'export RUN_TIMEOUT_MS=' "$wrapper_path" || echo "MISSING: RUN_TIMEOUT_MS"

Correct paths

# Extract SCRIPT_DIR from wrapper
SCRIPT_DIR=$(grep '^SCRIPT_DIR=' "$wrapper_path" | cut -d'"' -f2)

# Verify it matches REPO_ROOT
if [[ "$SCRIPT_DIR" != "$REPO_ROOT/.claude/skills/setup-agent-team" ]]; then
    echo "WARNING: SCRIPT_DIR mismatch"
    echo "  Found: $SCRIPT_DIR"
    echo "  Expected: $REPO_ROOT/.claude/skills/setup-agent-team"
fi

Exec pattern

# Verify it uses exec bun run
grep -q 'exec bun run "${SCRIPT_DIR}/trigger-server.ts"' "$wrapper_path" || echo "WARNING: Non-standard exec pattern"

Step 5: Check systemd service compliance

For each systemd service file at `/etc/systemd/system/<service-name>.service`:

Required fields

# Check critical fields
grep -q "^User=$SERVICE_USER$" "$service_file" || echo "MISSING/WRONG: User"
grep -q "^Group=$SERVICE_GROUP$" "$service_file" || echo "MISSING/WRONG: Group"
grep -q "^WorkingDirectory=$REPO_ROOT/.claude/skills/setup-agent-team$" "$service_file" || echo "MISSING/WRONG: WorkingDirectory"
grep -q "^ExecStart=/bin/bash $REPO_ROOT/.claude/skills/setup-agent-team/start-" "$service_file" || echo "MISSING/WRONG: ExecStart"

Environment variables

# Check PATH includes correct home directory
grep "^Environment=\"PATH=$HOME_DIR/.bun/bin:$HOME_DIR/.local/bin:" "$service_file" || echo "WARNING: PATH may be incorrect"

# Check HOME is set
grep "^Environment=\"HOME=$HOME_DIR\"$" "$service_file" || echo "MISSING/WRONG: HOME"

# Check IS_SANDBOX
grep -q '^Environment="IS_SANDBOX=1"' "$service_file" || echo "MISSING: IS_SANDBOX"

Step 6: Update wrapper scripts (if needed)

If `--check-only` is NOT passed and issues were found:

For path mismatches, update SCRIPT_DIR:

# This requires preserving the TRIGGER_SECRET value
# Read current secret
CURRENT_SECRET=$(grep '^export TRIGGER_SECRET=' "$wrapper_path" | cut -d'"' -f2)

# Update SCRIPT_DIR line
sed -i "s|^SCRIPT_DIR=.*|SCRIPT_DIR=\"$REPO_ROOT/.claude/skills/setup-agent-team\"|" "$wrapper_path"

# Update REPO_ROOT line
sed -i "s|^export REPO_ROOT=.*|export REPO_ROOT=\"$REPO_ROOT\"|" "$wrapper_path"

For missing env vars, add them:

# Add CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS if missing
if ! grep -q 'CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS' "$wrapper_path"; then
    # Insert before exec line
    sed -i '/^exec bun run/i export CLAUDE_CODE_EXPERIMENTAL_AGENT_T
Read more
Ships withspawn

Launch any AI agent on any cloud with a single command. Coding agents, research agents, self-hosted AI tools — Spawn deploys them all. All models powered by OpenRouter. (ALPHA software, use at your own risk!) 10 agents. 8 clouds. 79 working combinations.

Get the whole plugin
Stats
222
Stars
34
Forks
Active
Maintenance
TypeScript
Language
Apache-2.0
License
9d ago
Last commit
6mo ago
Created

Repo: OpenRouterLabs/spawn