init

A command that imports custom agents from a Claude Code environment into an orchestration system. It scans the agent definitions, lets the user select which ones to import, and registers them for workflows.

In plain words
What is it for?
Use it to find agent files in the Claude Code agents folder, choose agents, and make them available under the orchestration namespace.
Why use it?
It makes existing custom agents available to the orchestration system without manually copying each definition.

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/mbruhler/claude-orchestration/init
Clone the repo
git clone --depth 1 https://github.com/mbruhler/claude-orchestration
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 902 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 $0.00011 $0.00902
Opus 5 $0.00005 $0.00451
Sonnet 5 $0.00002 $0.00180
Haiku 4.5 $0.00001 $0.00090

Measured 2d ago against content hash 51f5c1e6207a, 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 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.

commands/init.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize Orchestration Plugin

Import custom agents from your Claude Code environment to make them available in orchestration workflows.

Usage

/orchestration:init

This command will:

  1. Scan ~/.claude/agents/ for custom agent definitions
  2. Let you select which agents to register
  3. Make agents available for use in all workflows

Action

IMPORTANT: Execute ALL steps in order. Use AskUserQuestion for user choices.

Step 1: Scan for Custom Agents

  1. Use Glob tool to find all .md files in ~/.claude/agents/
  2. Filter out built-in agents: explore, plan, general-purpose
  3. For each custom agent file:
    • Read the file using Read tool
    • Extract description from frontmatter or first heading
    • Store agent name and description
  4. If no custom agents found, inform user and exit

Step 2: Present Agents to User

IMPORTANT: MUST use AskUserQuestion tool for interactive selection!

If custom agents were found:

  1. Create options array from discovered agents
  2. Each option should have:
    • label: agent name (e.g., "expert-code-implementer")
    • description: agent description or "No description available"
  3. Use AskUserQuestion tool:
    • question: "Select agents to register in orchestration context. These agents will become available for use in workflows."
    • header: "Import Agents"
    • multiSelect: true (allow multiple selections)
    • options: the options array (max 4, if more agents exist, add "Import all" option)
  4. Parse the response to get list of selected agent names

Step 3: Register Selected Agents

For each selected agent:

  1. Read the agent file from ~/.claude/agents/{agent-name}.md
  2. Extract metadata (name, description)
  3. Create reference mapping (do NOT copy the file!)
  4. Store mapping with:
    • Agent name
    • Description
    • Path to original file: ~/.claude/agents/{agent-name}.md
    • Type: "external"

Step 4: Update Agent Registry

IMPORTANT: Use ${CLAUDE_PLUGIN_ROOT} for all plugin workspace paths!

Read the full file on GitHub · 124 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 · 124 lines · 11 tokens per session scan A 51f5c1e6207a

Subscribe to this mod's changes

init is a command published in the GitHub repository mbruhler/claude-orchestration (218 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 902 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.