What is maestro-skills AGENTS.md?

Repository instructions for developing ddtcorex/maestro-skills. They require a workflow of design discussion, written planning, and test-first implementation.

Guiding agents through changes in this repository, including design records, task plans, tests, implementation, and commits.

They give coding agents a consistent way to make changes and require TDD, which means writing a failing test before the code that makes it pass.

maestro-skills AGENTS.md — Instructions file for Claude Code and Codex by ddtcorex: Repository instructions for developing ddtcorex/maestro-

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 instructions/ddtcorex/maestro-skills/agents-md

Clone the repo

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

Made for: Claude Code, 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/ddtcorex/maestro-skills/agents-md.svg)](https://agentmods.dev/instructions/ddtcorex/maestro-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ddtcorex/maestro-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ddtcorex/maestro-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 5,116 This file is loaded in full into every session.

When invoked 5,116 The same file — it is already loaded in full.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.05116	$0.05116
Opus 5	$0.02558	$0.02558
Sonnet 5	$0.01023	$0.01023
Haiku 4.5	$0.00512	$0.00512

Measured yesterday against content hash 3ad64f9bd49d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

maestro-skills AGENTS.md scanned grade C with 2 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 yesterday.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

One-line installer/updater (`curl -fsSL .../install.sh | bash`). Key points if

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

One-line installer/updater (`curl -fsSL .../install.sh | bash`). Key points if

AGENTS.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents working in this repository. CLAUDE.md at the repo root is a symlink to this file, so Claude Code follows the same rules; Codex CLI reads AGENTS.md directly. Edit AGENTS.md only — never edit CLAUDE.md directly or replace the symlink with a copy.

Workflow: Superpowers skills are mandatory

Every change to this repository MUST follow the Superpowers skill workflow, in order:

brainstorming — explore intent and design before writing anything; record the outcome in the PR description (YYYY-MM-DD-<topic>-design.md style).
writing-plans — turn the approved spec into a task-by-task plan with exact test and implementation sketches; plans are transient working files, deleted once their batch ships.
executing-plans — implement task by task with strict TDD: failing test first, verify RED, implement, verify GREEN, then commit that task before starting the next.

Do not skip ahead to implementation or commit while a task's tests are red. Specs and plans are working artifacts, not deliverables — describe durable outcomes in the PR description instead of committing dated process files.

Git workflow

Never commit to master directly; start a feature branch per work session (fix/..., feat/..., docs/...). One TDD task = one commit while executing a plan; squash at merge time if the history reads better squashed.
Conventional commit subjects (fix:, feat:, docs:, chore:), imperative mood.
Open a pull request once the branch is green; link it to the plan that produced it.

What this repo is

A dual-ecosystem plugin (maestro-skills, npm @ddtcorex/maestro-skills) bundling 31 skills in two halves: 17 Magento 2 / Govard domain skills written here, plus the 14-skill superpowers process library forked verbatim from obra/superpowers v6.3.0 (MIT — see THIRD-PARTY-NOTICES.md). Distributed via self-listing marketplaces for both Claude Code and Codex CLI, and as a DeepSeek Harness Cordis plugin that also installs its own DSH agent preset at startup. There is no test suite and no application code beyond src/ (the Cordis plugin) — the repository is the plugin (in every ecosystem at once), and its content is Markdown (SKILL.md) plus four JSON manifests, one install script, and one sync script.

Read the full file on GitHub · 362 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.

yesterday Changed · +25 lines · +401 tokens per session 3ad64f9bd49d
5d ago First seen · 337 lines · 4,715 tokens per session scan C 79ae76d09074

Subscribe to this mod's changes

maestro-skills AGENTS.md is an instructions file published in the GitHub repository ddtcorex/maestro-skills (4 stars, last pushed yesterday), licensed MIT. It adds 5,116 tokens to every session, about $0.0256 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agent-skills ai-agent claude-code codex-plugin govard magento2

maestro-skills AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codehighSupply chain

Makes network callslowCapability

How it starts

AGENTS.md

Workflow: Superpowers skills are mandatory

Git workflow

What this repo is

What this file has done since we first saw it

Other instructions, from other repositories

supergraph AGENTS.md

project-legibility AGENTS.md

lianhuanhua-skills AGENTS.md

ai-plugin GEMINI.md

quantcoder-plugin GEMINI.md

vectorworks-mcp-codex-plugin AGENTS.md