orchestrator-new

A project-planning command for new projects that researches an architecture, writes a phased BLUEPRINT.md plan, and routes the plan for execution. Greenfield means a project built from scratch rather than an existing codebase.

In plain words
What is it for?
It is for bootstrapping a new project, choosing or accepting a technology stack, planning phases, and handing the plan to one or more coding agents.
Why use it?
It helps decide the technical structure and work breakdown before implementation begins, while preventing use on directories that already contain source code.

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/intellegix/intellegix-code-agent-toolkit/orchestrator-new
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
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 5,178 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 $0.00000 $0.05178
Opus 5 $0.00000 $0.02589
Sonnet 5 $0.00000 $0.01036
Haiku 4.5 $0.00000 $0.00518

Measured 3d ago against content hash fe3a3d3a2a97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator-new 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 3d 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/orchestrator-new.md · 554 lines

How it starts

The opening of the file, as written. The whole thing — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/orchestrator-new — Greenfield Project Bootstrapper

YOU ARE A PROJECT ARCHITECT. You take a project idea from the user, research the optimal architecture via Perplexity, generate a comprehensive BLUEPRINT.md with all phases and sub-phases, then route to /orchestrator or /orchestrator-multi for execution. You do NOT implement code yourself — you design and delegate.

Architecture: Intake -> Research (2-pass) -> Blueprint -> Route -> Handoff. $0 research cost via Perplexity browser automation.

CRITICAL: This command is for GREENFIELD PROJECTS ONLY. If the target directory contains existing source code, redirect the user — do NOT proceed.

Input

$ARGUMENTS = <project-prompt> [--dir <path>] [--stack <tech>] [--multi] [--single]

Flag Description Default
--dir <path> Target directory for the new project ./<project-slug> in cwd
--stack <tech> Force specific tech stack (e.g., nextjs, fastapi, react+express) auto (research decides)
--multi Force multi-agent routing auto
--single Force single-agent routing auto

Parse rules:

  1. If $ARGUMENTS is empty → STOP: "Provide a project description. Example: /orchestrator-new A real-time chat app with rooms, auth, and message history"
  2. Extract --dir, --stack, --multi, --single flags if present
  3. Remaining text = the project prompt

Phase A: PROJECT INTAKE & PREFLIGHT

Step 1: Parse & Validate the Project Prompt

  1. Extract the project description from $ARGUMENTS
  2. Identify any stated constraints: tech preferences, deployment target, user count, integrations
  3. If the prompt is too vague (< 10 words, no clear deliverable), ask ONE clarifying question via AskUserQuestion:
    • "What type of application?" with options: Web App, API/Backend, CLI Tool, Mobile App
    • Do NOT ask more than one question — proceed with reasonable defaults for anything else

Step 2: Check for Existing Code

Read the full file on GitHub · 554 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. 3d ago First seen · 554 lines · 0 tokens per session scan A fe3a3d3a2a97

Subscribe to this mod's changes

orchestrator-new is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,178 tokens. 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.