A command for setting up ruv-swarm hooks, which are automatic actions triggered by agent events. It initializes hook settings, provides tests, and lets you customize the hook configuration.

Use it to initialize hooks, test pre-edit and session-end behavior, customize .claude/settings.json, and inspect hook response fields.

It reduces the manual work of creating hook configuration and checking whether hooks respond correctly.

setup — Command by natea

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/natea/fitfinder/setup

Clone the repo

git clone --depth 1 https://github.com/natea/fitfinder

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 507 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00507
Opus 5	$0.00000	$0.00253
Sonnet 5	$0.00000	$0.00101
Haiku 4.5	$0.00000	$0.00051

Measured 2d ago against content hash d24b951e66c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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.

Origin

This is a copy

100% identical to setup — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/hooks/setup.md · 103 lines

What it actually says

Setting Up ruv-swarm Hooks

Quick Start

1. Initialize with Hooks

npx claude-flow init --hooks

This automatically creates:

.claude/settings.json with hook configurations
Hook command documentation
Default hook handlers

2. Test Hook Functionality

# Test pre-edit hook
npx claude-flow hook pre-edit --file test.js

# Test session summary
npx claude-flow hook session-end --summary

3. Customize Hooks

Edit .claude/settings.json to customize:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "^Write$",
        "hooks": [{
          "type": "command",
          "command": "npx claude-flow hook pre-write --file '${tool.params.file_path}'"
        }]
      }
    ]
  }
}

Hook Response Format

Hooks return JSON with:

continue: Whether to proceed (true/false)
reason: Explanation for decision
metadata: Additional context

Example blocking response:

{
  "continue": false,
  "reason": "Protected file - manual review required",
  "metadata": {
    "file": ".env.production",
    "protection_level": "high"
  }
}

Performance Tips

Keep hooks lightweight (< 100ms)
Use caching for repeated operations
Batch related operations
Run non-critical hooks asynchronously

Debugging Hooks

# Enable debug output
export CLAUDE_FLOW_DEBUG=true

# Test specific hook
npx claude-flow hook pre-edit --file app.js --debug

Common Patterns

Auto-Format on Save

Already configured by default for common file types.

Protected File Detection

{
  "matcher": "^(Write|Edit)$",
  "hooks": [{
    "type": "command",
    "command": "npx claude-flow hook check-protected --file '${tool.params.file_path}'"
  }]
}

Automatic Testing

{
  "matcher": "^Write$",
  "hooks": [{
    "type": "command",
    "command": "test -f '${tool.params.file_path%.js}.test.js' && npm test '${tool.params.file_path%.js}.test.js'"
  }]
}

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.

2d ago First seen · 103 lines · 0 tokens per session scan A d24b951e66c2

Subscribe to this mod's changes

setup is a command published in the GitHub repository natea/fitfinder (4 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 507 tokens. A static security scan graded it A with 0 findings. It is 100% identical to setup, differing in 0 lines, and is treated as a copy.

Testing

setup