What is maestro AGENTS.md?

Repository instructions for AI coding assistants working on the Maestro project, a Rust terminal application that lets people work with several AI systems. They define shared rules, project context, communication style, and how the instructions stay consistent across assistants.

Use them whenever an AI assistant works on Maestro, especially when changing its Rust command-line or terminal interface code and its shared agent rules.

They give different coding assistants one source of project guidance, reducing conflicting edits and making their changes fit the repository's conventions.

How CarlosDanielDev/maestro configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to CarlosDanielDev/maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CarlosDanielDev/maestro/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/CarlosDanielDev/maestro

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/carlosdanieldev/maestro/agents-md/github.svg)](https://agentmods.dev/instructions/carlosdanieldev/maestro/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/carlosdanieldev/maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/carlosdanieldev/maestro/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/carlosdanieldev/maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/carlosdanieldev/maestro/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,252 This file is loaded in full into every session.

When invoked 1,252 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01252	$0.01252
Opus 5.5	$0.00501	$0.00501
Sonnet 5.5	$0.00250	$0.00250
Haiku 4.5	$0.00125	$0.00125

Measured 1mo ago against content hash 56d694b9641c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maestro AGENTS.md 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

maestro GEMINI.md — 98% identical, 4 lines differ

AGENTS.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Entry point for any AI agent that reads AGENTS.md by default (Aider, GitHub Copilot, OpenAI Codex CLI, etc.).

Below is the canonical Golden Rules block. Source of truth: .maestro/templates/core/golden-rules.md. Do not edit this block here — edit the canonical file and re-run scripts/check-rules-drift.sh (or wait for the rules-drift CI job to catch the mismatch).

Golden Rules — Agent System Prompt

Canonical source for every AI agent working in this repo (Claude Code, Codex, Gemini, Aider, Copilot, any future provider). Copied verbatim into provider entry points (.claude/CLAUDE.md, .codex/AGENTS.md, AGENTS.md, GEMINI.md); drift enforced by scripts/check-rules-drift.sh in CI.

Who I am

Carlos. Software developer. Background in mobile/hybrid. Strong in TDD and clean code. Still learning architecture decisions and their impacts. English is a second language — keep words simple, no fancy vocabulary. Match my depth: don't over-explain what I know; don't skip context I need.

Project

maestro — living TUI tool that lets developers and non-tech users build software with multiple AIs in one place. Rust. CLI + ratatui TUI + tokio. Audience is mixed: technical and non-technical. Always avoid over-engineering and over-complexity. Flag anything that doesn't fit.

Tech stack (use these; never suggest alternatives unless I ask)

Language: Rust 2024 edition (MSRV 1.89)
Framework: ratatui + crossterm (TUI), tokio (async)
Package manager: cargo
Database: none — TOML state files via toml_edit
Testing: cargo test + insta (snapshots)
Styling: ratatui theme system (src/tui/theme.rs)

If something looks like the wrong tool, flag it before using anything else.

Communication preferences

Numbers before guesses. Pragmatic.
Short sentences.
Help with English when it helps; never use awkward or fancy words.
When writing on my behalf: first explain, then the cause, then the solutions.
Match this voice exactly. Do not default to your patterns.

Read the full file on GitHub · 90 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.

1mo ago First seen · 90 lines · 1,252 tokens per session scan A 56d694b9641c

Subscribe to this mod's changes

maestro AGENTS.md is an instructions file published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 1,252 tokens to every session, about $0.0050 per session on Opus 5.5. 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 2026-10-02.

Building agents

maestro AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
maestro AGENTS.mdCarlosDanielDev/maestro	Instructions file	31	20d ago	MIT	A	1,252	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

maestro: Instructions file for Codex