A command that sets up a coordination plan for Claude Code to follow on complex tasks. It organizes work across perspectives but does not create agents or write code itself.

Use it to initialize a coordination topology, choose a strategy, and guide how Claude Code breaks down and approaches a complex task.

It adds structure to large tasks and helps keep the work consistent without pretending to perform the implementation.

init — Command by EarthmanWeb

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/earthmanweb/claude-flow-plugin/init

Clone the repo

git clone --depth 1 https://github.com/EarthmanWeb/claude-flow-plugin

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 314 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 89% 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	$0.00314
Opus 5	$0.00000	$0.00157
Sonnet 5	$0.00000	$0.00063
Haiku 4.5	$0.00000	$0.00031

Measured yesterday against content hash f81c86395bc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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

89% identical to init — 4 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/coordination/init.md · 45 lines

What it actually says

Initialize Coordination Framework

🎯 Key Principle

This tool coordinates Claude Code's actions. It does NOT write code or create content.

MCP Tool Usage in Claude Code

Tool: mcp__claude-flow__swarm_init

Parameters

{"topology": "mesh", "maxAgents": 5, "strategy": "balanced"}

Description

Set up a coordination topology to guide Claude Code's approach to complex tasks

Details

This tool creates a coordination framework that helps Claude Code:

Break down complex problems systematically
Approach tasks from multiple perspectives
Maintain consistency across large projects
Work more efficiently through structured coordination

Remember: This does NOT create actual coding agents. It creates a coordination pattern for Claude Code to follow.

Example Usage

In Claude Code:

Use the tool: mcp__claude-flow__swarm_init
With parameters: {"topology": "mesh", "maxAgents": 5, "strategy": "balanced"}
Claude Code then executes the coordinated plan using its native tools

Important Reminders

✅ This tool provides coordination and structure
✅ Claude Code performs all actual implementation
❌ The tool does NOT write code
❌ The tool does NOT access files directly
❌ The tool does NOT execute commands

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.

yesterday First seen · 45 lines · 0 tokens per session scan A f81c86395bc9

Subscribe to this mod's changes

init is a command published in the GitHub repository EarthmanWeb/claude-flow-plugin (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 314 tokens. A static security scan graded it A with 0 findings. It is 89% identical to init, differing in 4 lines, and is treated as a copy.

Building agents Planning Writing and docs

verify

Adversarial spec-vs-implementation verification for a completed task. Dispatches the spec-mentor subagent with fresh context (no anchoring bias), parses its verdict (PASS / DRIFT / NEEDS-MARTY), and updates the verification queue. The v7.4.0 architectural replacement for a dedicated "mentor session.".

MartyBonacci/specswarm · 68 tokens

init