orc

orc is a command for coding agents from bengous/claude-code-plugins. It costs 8 tokens per session (3,248 once invoked), scanned A, original, MIT.

A command for coordinating complex feature work across multiple coding agents. It gathers codebase context, gets architectural agreement, creates isolated worktrees, runs implementation work, and reviews the results.

In plain words
What is it for?
Use it to plan, execute, merge, review, and prepare parallel agent changes for shipping.
Why use it?
It provides an organized process for splitting complex work while managing dependencies, integration, and final review.

Command

Part of the claude-orchestration plugin — 1 skill, 6 commands, 3 agents shipped together

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/bengous/claude-code-plugins/orc
Clone the repo
git clone --depth 1 https://github.com/bengous/claude-code-plugins

Or install claude-orchestration, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 3 agents.

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 orc

README.md
[![agentmods](https://agentmods.dev/badge/commands/bengous/claude-code-plugins/orc.svg)](https://agentmods.dev/commands/bengous/claude-code-plugins/orc)
Your own site
<a href="https://agentmods.dev/commands/bengous/claude-code-plugins/orc"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/orc.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,248 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 $0.00008 $0.03248
Opus 5 $0.00004 $0.01624
Sonnet 5 $0.00002 $0.00650
Haiku 4.5 $0.00001 $0.00325

Measured yesterday against content hash 218e649998e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orc 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.

orchestration/commands/orc.md · 451 lines

How it starts

The opening of the file, as written. The whole thing — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel orchestration workflow

Dependency: Requires git-worktree plugin installed (/plugin install git-worktree@bengous-plugins then /git-worktree:worktree-setup).


<phase_1 title="Understand & Plan">

Goal: Gather context, get architect consensus, and get approval

Initial request: $ARGUMENTS

Step 1: Create Task List

Before anything else, create tasks to track all 3 phases:

TaskCreate(
  subject: "Phase 1: Understand & Plan",
  description: "Explore codebase, get architect consensus, obtain approval",
  activeForm: "Planning",
  metadata: {"phase": 1}
)
TaskCreate(
  subject: "Phase 2: Execute",
  description: "Create worktrees, spawn implementation agents, merge results",
  activeForm: "Executing",
  metadata: {"phase": 2}
)
TaskCreate(
  subject: "Phase 3: Review & Ship",
  description: "Quality review, create PR, present summary",
  activeForm: "Shipping",
  metadata: {"phase": 3}
)

# Mark Phase 1 as in_progress (always read state before updating)
TaskGet(taskId: "phase-1-id")
TaskUpdate(taskId: "phase-1-id", status: "in_progress")

Step 2: Inline Exploration

Explore the codebase directly using Glob and Grep. Batch file reads when possible - read multiple files in a single tool call for faster context building.

  1. Find relevant files (Glob for patterns, Grep for keywords)
  2. Read key files to understand patterns, conventions, integration points
  3. Summarize: relevant code, patterns to follow, files to change

Step 3: Clarify If Needed

Ask about scope, design preferences, or edge cases only if truly ambiguous. Proceed autonomously when requirements are reasonably clear.

Read the full file on GitHub · 451 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. yesterday First seen · 451 lines · 8 tokens per session scan A 218e649998e3

Subscribe to this mod's changes

orc is a command published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 3,248 once invoked, about $0.0000 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 2026-09-03.