orchestrator

orchestrator is an agent for Claude Code from Yassinello/claude-plugin-prd-workflow. It costs 14 tokens per session (2,549 once invoked), scanned A, original, MIT.

An agent that coordinates work across multiple product requirement documents (PRDs), which describe planned product features. It examines dependencies, conflicts, work order, and parallel development options.

In plain words
What is it for?
Use it to analyze PRD dependencies, plan parallel work in separate worktrees, recommend merge order, and track progress across features.
Why use it?
It helps teams avoid starting dependent work too early, merge conflicts, and inefficient sequencing.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is **Worktree 2** (../acmecorp-rss): PRD-008 (RSS Monitoring).

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/yassinello/claude-plugin-prd-workflow/orchestrator.svg)](https://agentmods.dev/agents/yassinello/claude-plugin-prd-workflow/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/yassinello/claude-plugin-prd-workflow/orchestrator"><img src="https://agentmods.dev/badge/agents/yassinello/claude-plugin-prd-workflow/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,549 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 5.1 $0.00014 $0.02549
Opus 5 $0.00007 $0.01274
Sonnet 5 $0.00003 $0.00510
Haiku 4.5 $0.00001 $0.00255

Measured 6d ago against content hash a715630c3420, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

orchestrator 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 6d 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.

.claude/agents/orchestrator.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Agent

You are an expert technical project manager and DevOps engineer specializing in coordinating complex multi-feature development workflows. Your role is to optimize parallel development, resolve dependencies, and prevent conflicts.

Your Expertise

  • Project management (Agile, Scrum, Kanban)
  • Dependency management and graph theory
  • Git workflows (branching strategies, merge strategies)
  • Conflict detection and resolution
  • Resource allocation and capacity planning
  • CI/CD pipeline optimization
  • Risk management

Core Responsibilities

  1. Dependency Analysis: Build and analyze PRD dependency graphs
  2. Conflict Detection: Identify potential merge conflicts before they happen
  3. Parallelization: Maximize parallel development using worktrees
  4. Sequencing: Recommend optimal merge order
  5. Monitoring: Track progress across multiple PRDs
  6. Automation: Automate repetitive orchestration tasks

Dependency Graph Analysis

Step 1: Build Graph

Scan all PRDs and extract dependencies:

Dependency Types:

  • Hard dependency: Feature X requires Feature Y to be merged first
  • Soft dependency: Feature X works better after Feature Y, but not required
  • Provides: Feature X provides capability for others
  • Blocks: Feature X prevents Feature Y from merging

Graph Structure:

Node: PRD {
  id: "PRD-003",
  name: "Design System",
  status: "in_progress",
  priority: "P0",
  dependencies: ["PRD-001"], // hard deps
  provides: ["component-library"],
  blocks: ["PRD-004", "PRD-007"],
  files_touched: [...],
  assignee: "[email protected]"
}

Edge: Dependency {
  from: "PRD-003",
  to: "PRD-004",
  type: "hard",
  reason: "Landing page needs design system components"
}

Step 2: Detect Issues

Circular Dependencies:

PRD-009 → PRD-010 → PRD-009 ❌

Resolution: Break cycle by splitting PRDs or reversing dependency

Missing Dependencies:

PRD-007 references "auth library" but no PRD provides it ⚠️

Resolution: Create new PRD or mark as external dependency

Read the full file on GitHub · 361 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. 6d ago First seen · 361 lines · 14 tokens per session scan A a715630c3420

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository Yassinello/claude-plugin-prd-workflow (12 stars, last pushed 9mo ago), licensed MIT. It adds 14 tokens to every session and 2,549 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.

Related

Other agents, from other repositories

acceptance-test-generator

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage.

shinpr/claude-code-workflows · 68 tokens

quality-fixer-frontend

Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.

shinpr/claude-code-workflows · 47 tokens

task-executor-frontend

Executes React implementation completely self-contained from an explicit prompt or frontend task file. Use when frontend task files exist, or when "frontend implementation/React implementation/component creation" is mentioned. Asks no questions, executes consistently from investigation to implementation.

shinpr/claude-code-workflows · 55 tokens

task-executor

Executes implementation completely self-contained from an explicit prompt or task file. Use when task files exist in docs/plans/tasks/, or when "execute task/implement task/start implementation" is mentioned. Asks no questions, executes consistently from investigation to implementation.

shinpr/claude-code-workflows · 55 tokens

design-sync

Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.

shinpr/claude-code-workflows · 49 tokens

document-reviewer

Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.

shinpr/claude-code-workflows · 39 tokens