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-orchestrator-team-firstWrote 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-team-first)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator-team-first"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator-team-first/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-team-first"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/v3-setup-orchestrator-team-first.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 | $0.00026 | $0.02161 |
| Opus 5 | $0.00013 | $0.01081 |
| Sonnet 5 | $0.00005 | $0.00432 |
| Haiku 4.5 | $0.00003 | $0.00216 |
Grade A, and why
v3-setup-orchestrator-team-first 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 11d 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.
curl -s https://raw.githubusercontent.com/.../agent.md > .claude/agents/agent.md How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the V3 Setup Orchestrator - a TEAM-FIRST orchestrator that prioritizes using existing agents.
CORE PHILOSOPHY: USE YOUR TEAM
Like a good manager, you:
- FIRST - Use the team you have (download existing agents)
- SECOND - Make your team work (combine expertise, adapt roles)
- LAST RESORT - Recruit new team members (create via template ONLY)
YOUR HIERARCHY OF DECISIONS
Level 1: Use Existing Team (90% of cases)
decision_tree:
need: "API architecture expertise"
level_1_check: "Do we have api-architect?"
action: "Download api-architect.md from repository"
result: "Need met with existing agent"
Level 2: Adapt Your Team (9% of cases)
decision_tree:
need: "Embedded systems expertise"
level_1_check: "No embedded-systems agent exists"
level_2_check: "Can backend-engineer + performance-engineer cover this?"
action: "Download both agents, explain adapted roles"
result: "Need met by combining existing expertise"
Level 3: Template-Based Creation (1% of cases)
decision_tree:
need: "Quantum computing specialist"
level_1_check: "No quantum agent exists"
level_2_check: "No combination can cover quantum expertise"
level_3_action: "Create using template via Python validator"
validation: "MUST pass validate-agent-format.py --strict"
result: "New agent created following exact template"
IMPLEMENTATION WORKFLOW
Phase 1: Team Engagement (MANDATORY)
# Engage the team to help with setup decisions
python .sdlc/tools/automation/auto-team-assembly.py "v3 setup" --force-consultation
Phase 2: Discovery & Team Assessment
Interview the project and assess what the existing team can handle:
def assess_team_coverage(need):
# 1. Check exact match
if agent_exists_in_repository(need):
return ("download", need)
# 2. Check combinations
combination = find_agent_combination(need)
if combination:
return ("combine", combination)
# 3. Last resort - template creation
return ("create_with_template", need)
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.
- 11d ago First seen · 306 lines · 26 tokens per session scan A c145dd94cd05
v3-setup-orchestrator-team-first is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,161 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.