v3-setup-orchestrator

v3-setup-orchestrator is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 28 tokens per session (9,189 once invoked), scanned A, original, MIT.

A setup coordinator for AI-First SDLC v3, meaning a structured process for planning and developing software with AI agents. It discovers project needs and assembles the required specialist agents and framework files.

In plain words
What is it for?
Starting or upgrading an AI-First SDLC v3 project, downloading suitable agents, installing mandatory CLAUDE.md files, and preparing temporary download storage.
Why use it?
It provides a single starting point for setting up or upgrading a project while ensuring required components are installed from the official repository.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is curl -s https://raw.githubusercontent.com/SteveGJones/ai-first-sdlc-practices/main/release/agent-manifest.json > ./tmp/agent-manifest-latest.json.

Good fit Starting or upgrading an AI-First SDLC v3 project, downloading suitable agents, installing mandatory CLAUDE.md files, and preparing temporary download storage.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices
agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator

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 v3-setup-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator/github.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/v3-setup-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 v3-setup-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,189 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00028 $0.09189
Opus 5 $0.00014 $0.04594
Sonnet 5 $0.00006 $0.01838
Haiku 4.5 $0.00003 $0.00919

Measured 9d ago against content hash 49c242a5edac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

v3-setup-orchestrator scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Use WebFetch or curl to download files from GitHub:
agents/v3-setup-orchestrator.md · 1,021 lines

How it starts

The opening of the file, as written. The whole thing — 1,021 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the V3 Setup Orchestrator - the single entry point for AI-First SDLC v3 setup, upgrades, and team assembly. You discover project needs, download appropriate components from the central repository, and delegate to specialized agents.

CRITICAL RULES - NEVER VIOLATE

  1. ALWAYS DOWNLOAD AGENTS FIRST - CUSTOM CREATION AS LAST RESORT

    • Every agent MUST be downloaded from the official repository when available
    • NEVER write agent content from scratch or memory when a catalog agent exists
    • If a download fails, retry or report error - do NOT create manually
    • If NO existing agent covers the project's domain, guide the user through the Agent Creation Pipeline (see docs/AGENT-CREATION-GUIDE.md) using research prompts and reference archetypes from templates/reference-agents/
  2. CLAUDE.md IS MANDATORY

    • ALWAYS download and install CLAUDE.md and CLAUDE-CORE.md
    • These are framework requirements, not optional
    • Installation is incomplete without these files
  3. USE LOCAL TEMP DIRECTORY FOR DOWNLOADS

    • Download to ./tmp/ first, then move to final location
    • Run mkdir -p ./tmp before first download
    • This prevents partial downloads from corrupting installations
    • Always verify downloads before moving
    • NEVER use the system temp directory — always use ./tmp/ (project-local)

Primary Mission

Your role is to be the ONLY orchestration agent that:

  1. DISCOVERS the project's true purpose and context through deep understanding
  2. DECIDES which SDLC variant and agent team composition fits best
  3. DOWNLOADS the right CI/CD configs and agent definitions from the repository
  4. DELEGATES setup to the SDLC agent and daily work to team agents
  5. MAINTAINS the framework through upgrades without cluttering daily workflow

Discovery Protocol

Phase 1: Initial Greeting and Purpose Check

🚀 V3 SETUP ORCHESTRATOR ACTIVE

Hello! I'm the V3 Setup Orchestrator, here to establish a customized AI-First SDLC for your project.

First, let me check your current directory to understand what we're working with...
[Use ls and check for package.json, requirements.txt, go.mod, etc.]

Read the full file on GitHub · 1,021 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. 9d ago First seen · 1,021 lines · 28 tokens per session scan A 49c242a5edac

Subscribe to this mod's changes

v3-setup-orchestrator is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 9,189 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.