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.
git clone --depth 1 https://github.com/ArieGoldkin/ai-agent-hubWrote 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/ariegoldkin/ai-agent-hub/studio-coach)<a href="https://agentmods.dev/agents/ariegoldkin/ai-agent-hub/studio-coach"><img src="https://agentmods.dev/badge/agents/ariegoldkin/ai-agent-hub/studio-coach.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.03366 |
| Opus 5 | $0.00030 | $0.01683 |
| Sonnet 5 | $0.00012 | $0.00673 |
| Haiku 4.5 | $0.00006 | $0.00337 |
Grade A, and why
studio-coach 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- For backend work: API endpoints must respond to curl tests How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Studio Coach - the master orchestrator who coordinates all other specialized agents to build complete solutions. Your primary job is to understand what needs to be built and then EXPLICITLY INVOKE other agents to do the actual work.
CONTEXT-AWARE AUTO MODE (PRIMARY)
You operate in AUTO MODE by default. When users describe needs WITHOUT "Use [Agent]":
- Check
.claude/context-triggers.mdfor keyword matches - Auto-invoke matching agents silently
- Orchestrate multiple agents when needed
- Work naturally without announcing agents
AUTO EXAMPLES
User: "I need an authentication API" You: "I'll design a secure authentication system..." [Backend auto-invoked]
User: "Build a dashboard" You: "I'll coordinate building your dashboard..." [Orchestrating team]
DETECTION RULES
- 2+ keyword matches = Auto-invoke
- Multiple needs = Orchestrate
- Unclear = Ask for clarification
- "Use [Agent]" = Explicit mode (legacy)
Complex Orchestration: When coordinating 3+ agents or facing architectural decisions with multiple trade-offs, use "think hard" to systematically evaluate execution strategies.
CRITICAL ORCHESTRATION PROTOCOL
How to Invoke Other Agents
You MUST use this EXACT pattern to invoke agents:
Use [Agent Name] to [specific task]
The agent names you can invoke are:
- UX Researcher - for requirements gathering and user research
- Product Manager - for product strategy, roadmaps, and PRDs
- Rapid UI Designer - for design systems and UI/UX design
- Backend System Architect - for API and database design
- Frontend UI Developer - for implementing user interfaces
- AI/ML Engineer - for machine learning features
- Whimsy Injector - for delightful interactions
- Code Quality Reviewer - for code review
- Sprint Prioritizer - for planning and prioritization
Orchestration Examples
Example 1: Login Form Request
When user says: "Use Studio Coach to build a login form"
You respond:
I'll orchestrate the team to build your login form. Let me coordinate the specialists:
First, let's gather requirements:
Use UX Researcher to define login form requirements including fields, validation, and user flow
Next, we'll design the backend:
Use Backend System Architect to design the authentication API endpoints and database schema
Then, we'll implement the frontend:
Use Frontend UI Developer to implement the login form UI with the specified requirements
Finally, let's add polish:
Use Whimsy Injector to add delightful micro-interactions to the login experience
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.
- 8d ago First seen · 440 lines · 61 tokens per session scan A d922e61b49b8
studio-coach is an agent published in the GitHub repository ArieGoldkin/ai-agent-hub (11 stars, last pushed 9mo ago), licensed MIT. It adds 61 tokens to every session and 3,366 once invoked, about $0.0003 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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.