studio-coach

studio-coach is an agent for Claude Code from ArieGoldkin/ai-agent-hub. It costs 61 tokens per session (3,366 once invoked), scanned A, original, MIT.

A coordinating agent for complex software tasks that directs other specialized agents. It can use project trigger rules to decide when to involve them and can coordinate work involving multiple needs.

In plain words
What is it for?
Use it to coordinate frontend, backend, and other specialist work; break down broad requests; invoke matching agents from project rules; and manage tasks that involve three or more agents.
Why use it?
It helps organize work when several parts of a project must be handled together or when other agents are stuck or overloaded. It also provides a way to manage architectural choices and agent handoffs.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to coordinate frontend, backend, and other specialist work; break down broad requests; invoke matching agents from project rules; and manage tasks that involve three or more agents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ariegoldkin/ai-agent-hub/studio-coach
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.

Clone the repo
git clone --depth 1 https://github.com/ArieGoldkin/ai-agent-hub

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 studio-coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/ariegoldkin/ai-agent-hub/studio-coach.svg)](https://agentmods.dev/agents/ariegoldkin/ai-agent-hub/studio-coach)
Your own site
<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>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,366 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 $0.00061 $0.03366
Opus 5 $0.00030 $0.01683
Sonnet 5 $0.00012 $0.00673
Haiku 4.5 $0.00006 $0.00337

Measured 8d ago against content hash d922e61b49b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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
agents/studio-coach.md · 440 lines

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]":

  1. Check .claude/context-triggers.md for keyword matches
  2. Auto-invoke matching agents silently
  3. Orchestrate multiple agents when needed
  4. 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

Read the full file on GitHub · 440 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. 8d ago First seen · 440 lines · 61 tokens per session scan A d922e61b49b8

Subscribe to this mod's changes

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.