teach-maestro

teach-maestro is a skill for Claude Code, Codex from sharpdeveye/maestro. It costs 29 tokens per session (712 once invoked), scanned A, original, MIT.

An onboarding guide for Maestro, a system for organising AI workflows, that creates a project context file through a structured interview.

In plain words
What is it for?
Use it once when starting a Maestro project or when the project has no .maestro.md context file.
Why use it?
It gathers the project details that later workflow commands need, such as models, tools, architecture, tests, and constraints.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/sharpdeveye/maestro/teach-maestro
Any agent
npx skills add sharpdeveye/maestro --skill teach-maestro
Clone the repo
git clone --depth 1 https://github.com/sharpdeveye/maestro

Made for: Claude Code, Codex.

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 teach-maestro

README.md
[![agentmods](https://agentmods.dev/badge/skills/sharpdeveye/maestro/teach-maestro.svg)](https://agentmods.dev/skills/sharpdeveye/maestro/teach-maestro)
Your own site
<a href="https://agentmods.dev/skills/sharpdeveye/maestro/teach-maestro"><img src="https://agentmods.dev/badge/skills/sharpdeveye/maestro/teach-maestro.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00712
Opus 5 $0.00015 $0.00356
Sonnet 5 $0.00006 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured 4d ago against content hash 690bcd398db9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

teach-maestro scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

source/skills/teach-maestro/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BOOTSTRAP — First Command to Run

This is the entry point for Maestro. It creates the .maestro.md context file that all other Maestro commands depend on. No other preparation is needed — this IS the preparation.


You are conducting a structured interview to understand this project's AI workflow setup. Be conversational but thorough.

Interview Questions

Ask these questions one section at a time. Wait for answers before proceeding.

Section 1 — Models & Providers

  • What AI model(s) are you using? (e.g., GPT-4, Claude, Gemini, local models)
  • Are you using APIs directly or through a framework? (e.g., LangChain, LlamaIndex, custom)
  • What are your context window sizes?

Section 2 — Workflow Architecture

  • Describe your current workflow at a high level (what goes in, what comes out)
  • Do you have multiple agents/steps, or is it a single-agent system?
  • What tools/functions are available to your agent(s)?

Section 3 — Quality & Evaluation

  • How do you currently evaluate output quality?
  • Do you have test cases or golden examples?
  • What are the most common failure modes?

Section 4 — Constraints

  • What are your cost constraints? (budget per request, per day)
  • What are your latency requirements? (real-time, batch, async)
  • Are there compliance requirements? (HIPAA, GDPR, SOC2, etc.)

Section 5 — Priorities

  • Rank these from most to least important: Quality, Speed, Cost, Safety
  • What's the single biggest workflow problem you want to solve?

Output Format

After gathering all answers, generate a .maestro.md file:

# Maestro Workflow Context
Generated: [date]

## Models & Providers
[answers from section 1]

## Workflow Architecture
[answers from section 2]

## Quality & Evaluation
[answers from section 3]

## Constraints
[answers from section 4]

## Priorities
[answers from section 5, with ranked priorities]

Save this file to the project root as .maestro.md.

Context Completeness

Section Status Impact if Missing
Models & Providers ? Commands can't tailor advice to your stack
Workflow Architecture ? Commands can't assess complexity
Quality & Evaluation ? /iterate and /evaluate less effective
Constraints ? /guard and /accelerate can't set limits
Priorities ? All commands default to generic guidance

Read the full file on GitHub · 103 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. 4d ago First seen · 103 lines · 29 tokens per session scan A 690bcd398db9

Subscribe to this mod's changes

teach-maestro is a skill published in the GitHub repository sharpdeveye/maestro (415 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 712 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-self-scheduling

Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.

sickn33/agentic-awesome-skills · 24 tokens

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

agnt-gg/agnt · 64 tokens

agnt-plugin-builder

End-to-end workflow for creating, building, installing, and hot-reloading AGNT plugins entirely from chat. Use this skill whenever the user asks to 'build a plugin', 'create an AGNT plugin', 'add a new tool to AGNT', 'integrate X with AGNT' (where X is an API or service), 'make a plugin for [service]', or wants to…

agnt-gg/agnt · 201 tokens

annie-universal-api-orchestrator

Use AGNT's stored OAuth tokens and API keys to call ANY third-party API directly from the orchestrator, without building a tool or plugin first. Use this skill whenever the user asks you to "do something with my GitHub / Gmail / Drive / Slack / Notion / Stripe / Shopify / Discord / Linear / Jira / Vercel / Netlify /…

agnt-gg/agnt · 208 tokens

frontend-slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

agnt-gg/agnt · 63 tokens

image-to-cinematic-video

Turn a prompt or an existing image into a polished multi-scene cinematic short video using Seedance for clip generation, uguu.se for file hosting, and FFmpeg for last-frame extraction and crossfade stitching. Supports two modes — PARALLEL (multiple scenes from the same reference image, concurrent, 3 min total) and…

agnt-gg/agnt · 297 tokens