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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesnpx agentmods add agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestratorWrote 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.
[](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.09189 |
| Opus 5.5 | $0.00011 | $0.03676 |
| Sonnet 5.5 | $0.00006 | $0.01838 |
| Haiku 4.5 | $0.00003 | $0.00919 |
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 1mo 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: 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
-
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/
-
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
-
USE LOCAL TEMP DIRECTORY FOR DOWNLOADS
- Download to ./tmp/ first, then move to final location
- Run
mkdir -p ./tmpbefore 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:
- DISCOVERS the project's true purpose and context through deep understanding
- DECIDES which SDLC variant and agent team composition fits best
- DOWNLOADS the right CI/CD configs and agent definitions from the repository
- DELEGATES setup to the SDLC agent and daily work to team agents
- 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.]
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.
- 1mo ago First seen · 1,021 lines · 28 tokens per session scan A 49c242a5edac
v3-setup-orchestrator is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 24d ago), licensed MIT. It adds 28 tokens to every session and 9,189 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.