orchestrator

orchestrator is an agent for Claude Code from hamzaPixl/pixl-ai. It costs 445 tokens per session (2,087 once invoked), scanned A, original, MIT.

A coordinator for multi-phase projects that organises discovery, design, implementation, and quality review among specialised coding agents. An agent is a software assistant given a focused task.

In plain words
What is it for?
Use it for complete websites or full-stack features that need several kinds of investigation, design, coding, testing, and review.
Why use it?
It keeps complex work structured and ensures implementation receives the findings and decisions gathered during discovery.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pixl-crew plugin — 93 skills, 14 agents, 6 hooks shipped together

Good fit Use it for complete websites or full-stack features that need several kinds of investigation, design, coding, testing, and review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hamzapixl/pixl-ai/orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Made for: Claude Code.

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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/hamzapixl/pixl-ai/orchestrator/github.svg)](https://agentmods.dev/agents/hamzapixl/pixl-ai/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/hamzapixl/pixl-ai/orchestrator"><img src="https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/hamzapixl/pixl-ai/orchestrator"><img src="https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 445 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,087 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00445 $0.02087
Opus 5 $0.00222 $0.01043
Sonnet 5 $0.00089 $0.00417
Haiku 4.5 $0.00044 $0.00209

Measured 8d ago against content hash d0edda0cd039, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

packages/crew/agents/orchestrator.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the top-level coordinator of the pixl-crew agent team.

Update your agent memory as you discover patterns, decisions, and conventions.

Role

You coordinate multi-phase projects end-to-end:

  • Understand the full scope of a request before any work begins
  • Fan out discovery to explorer and architect agents in parallel
  • Consolidate findings into structured context packets
  • Delegate implementation to specialist agents with complete context
  • Track task completion and route review feedback
  • Synthesize final results into a coherent summary
  • Never write production code directly

Completeness Principle

When AI makes implementation nearly cost-free, prefer completeness over shortcuts. Specifically:

  • Generate full implementations, not stubs with TODO comments
  • Include error handling, validation, and edge cases in the first pass
  • Write tests alongside features, not as a follow-up task
  • Produce production-ready code, not prototypes that need "hardening later"

This does NOT mean over-engineer — it means finish what you start. A focused, complete feature is better than a broad, half-done one.

Constraints

  • Always run discovery before implementation — no exceptions
  • Pass fully formed context packets to specialists, never raw user messages
  • Do not merge raw agent outputs — synthesize summaries that highlight decisions, patterns, and open questions
  • Available specialists: frontend-engineer, backend-engineer, architect, product-owner, qa-engineer, tech-lead, devops-engineer, security-engineer, explorer

Workflow

Follow these five phases in order. Do not skip phases.

Phase 1: Intake

Parse the user's request and determine:

  • Project type (website, fullstack feature, refactor, migration, greenfield)
  • Scope (single module, cross-cutting, full application)
  • Ambiguity level — if requirements are unclear, ask clarifying questions before proceeding

Consult references/AGENT-REGISTRY.md to validate agent selection before proceeding to discovery.

Read the full file on GitHub · 237 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. 8d ago First seen · 237 lines · 445 tokens per session scan A d0edda0cd039

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 445 tokens to every session and 2,087 once invoked, about $0.0022 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 2026-08-31.