update-team

A maintenance command for updating services that let multiple AI agents work together in a repository. It reads the latest team setup, updates service scripts, restarts services, and checks their health.

In plain words
What is it for?
Use it to update one named service or all deployed services, or to preview the changes with a check-only option.
Why use it?
It prevents running agent services with outdated settings, paths, or environment variables.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/openrouterlabs/spawn/update-team
Any agent
npx skills add OpenRouterLabs/spawn --skill update-team
Clone the repo
git clone --depth 1 https://github.com/OpenRouterLabs/spawn

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,641 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.02641
Opus 5 $0.00009 $0.01321
Sonnet 5 $0.00003 $0.00528
Haiku 4.5 $0.00002 $0.00264

Measured 2d ago against content hash 34b69c3cc151, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

update-team scanned grade C with 3 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo sed -i "s/^User=.*/User=$SERVICE_USER/" "$service_file"

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls -1 "$REPO_ROOT/.claude/skills/setup-agent-team/start-"*.sh 2>/dev/null | while read -r wrapper; do

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf http://localhost:8080/health || echo "ERROR: Health check failed for $service_name"
.claude/skills/update-team/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Read the full file on GitHub · 325 lines

Changes

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.

  1. 2d ago First seen · 325 lines · 17 tokens per session scan C 34b69c3cc151

Subscribe to this mod's changes

update-team is a skill published in the GitHub repository OpenRouterLabs/spawn (233 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,641 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.