crew-setup

crew-setup is a command for coding agents from arpitnath/claude-capsule-kit. It costs 16 tokens per session (690 once invoked), scanned A, original, MIT.

A command that checks whether the environment has what the /crew command needs. Crew runs multiple coding agents on parallel branches, and the command also checks related tools and setup.

In plain words
What is it for?
Use it to check agent-team support, verify the Claude Capsule Kit installation, and find missing Go helper programs.
Why use it?
It identifies missing configuration or software before you try to start an agent team.

Command

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 commands/arpitnath/claude-capsule-kit/crew-setup
Clone the repo
git clone --depth 1 https://github.com/arpitnath/claude-capsule-kit

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for crew-setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/arpitnath/claude-capsule-kit/crew-setup.svg)](https://agentmods.dev/commands/arpitnath/claude-capsule-kit/crew-setup)
Your own site
<a href="https://agentmods.dev/commands/arpitnath/claude-capsule-kit/crew-setup"><img src="https://agentmods.dev/badge/commands/arpitnath/claude-capsule-kit/crew-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 690 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00016 $0.00690
Opus 5 $0.00008 $0.00345
Sonnet 5 $0.00003 $0.00138
Haiku 4.5 $0.00002 $0.00069

Measured 4d ago against content hash c6ee901d26de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crew-setup scanned grade A with 0 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/crew-setup.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crew Setup

Check if your environment is ready for /crew (parallel multi-branch agent teams) and guide you through any missing pieces.

Step 1: Check Agent Teams

Agent Teams must be enabled in Claude Code for /crew to work.

Verify by checking if TeamCreate, SendMessage, and team-aware Task tools are available in your current session. If you can see these tools, agent teams are enabled.

If agent teams are NOT enabled:

  1. Tell the user: "Agent Teams are not enabled in your Claude Code instance."
  2. Share the setup guide: https://code.claude.com/docs/en/agent-teams
  3. Once enabled, ask the user to restart Claude Code and run /crew-setup again.

Step 2: Check CCK Installation

if [ -d "$HOME/.claude/cck/hooks" ] && [ -f "$HOME/.claude/cck/package.json" ]; then
  VERSION=$(node -e "console.log(JSON.parse(require('fs').readFileSync('$HOME/.claude/cck/package.json','utf8')).version)" 2>/dev/null || echo "unknown")
  echo "CCK installed: v$VERSION"
else
  echo "CCK not installed"
fi

If CCK is not installed, guide the user:

npm install -g claude-capsule-kit
cck setup

Step 3: Check Go Binaries

ls -la $HOME/.claude/bin/dependency-scanner $HOME/.claude/bin/progressive-reader 2>/dev/null || echo "MISSING"

If binaries are missing:

  1. Check if Go is available: go version
  2. If Go is available, build them:
    cck build
    
  3. If Go is NOT available:
    • Tell the user: "Go binaries (dependency-scanner, progressive-reader) are optional but recommended."
    • "Install Go 1.20+ from https://go.dev/dl/ then run cck build"
    • "Without them: dependency analysis and large file navigation won't be available."

Step 4: Check .crew-config.json

cat .crew-config.json 2>/dev/null || echo "NO_CONFIG"

If no config exists:

  • Tell the user: "No .crew-config.json found. You can create one with cck crew init or the /crew skill will create one interactively."

If config exists:

  • Show the team composition summary (name, teammates, roles, branches)

Read the full file on GitHub · 81 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. 4d ago First seen · 81 lines · 16 tokens per session scan A c6ee901d26de

Subscribe to this mod's changes

crew-setup is a command published in the GitHub repository arpitnath/claude-capsule-kit (88 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 690 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.