Maestro AGENTS.md

Maestro AGENTS.md is an instructions file for Codex, OpenCode from aaryansinha16/Maestro. It costs 967 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for AI agents working on the Maestro codebase, including which project files to read and how to implement common changes.

In plain words
What is it for?
Use it when modifying Maestro, especially when adding conductor features or changing prompt templates that affect agent behavior.
Why use it?
It gives agents a consistent process for understanding the architecture and coordinating changes across shared types, the database, APIs, and the dashboard.

Instructions file for CodexOpenCode

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/aaryansinha16/maestro/agents-md
Clone the repo
git clone --depth 1 https://github.com/aaryansinha16/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.

agentmods badge for Maestro AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aaryansinha16/maestro/agents-md.svg)](https://agentmods.dev/instructions/aaryansinha16/maestro/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/aaryansinha16/maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/aaryansinha16/maestro/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 967 This file is loaded in full into every session.
When invoked 967 The same file — it is already loaded in full.
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 5.1 $0.00967 $0.00967
Opus 5 $0.00483 $0.00483
Sonnet 5 $0.00193 $0.00193
Haiku 4.5 $0.00097 $0.00097

Measured 5d ago against content hash 5ee944b25add, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

AGENTS.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maestro — AGENTS.md

Purpose

Patterns for AI coding agents working on the Maestro codebase itself. Ensures consistent behavior across sessions.

This file is for agents building Maestro. The system prompts that drive agents working on managed projects are in packages/shared/src/prompt-templates.ts.

Before Any Task

  1. Read CLAUDE.md for architecture context
  2. Read DECISIONS.md for recent architectural decisions
  3. Read PROJECT_CONFIG.md for the developer's specific projects and their autonomy decisions
  4. Check the relevant package's src/ directory before creating new files
  5. If modifying an existing file, read it fully first

Task Patterns

When adding a new feature to the conductor

  1. Define the types in packages/shared/src/types.ts first
  2. Add Zod schemas in the same file
  3. Add the database table/migration in packages/conductor/src/db.ts
  4. Implement the conductor logic
  5. Add the API endpoint in packages/api/src/routes/
  6. Add the UI integration in packages/dashboard/src/
  7. Test end-to-end before considering done

When modifying prompt templates

This is the most sensitive part of the system. Changes here directly affect agent behavior on managed projects.

  1. Read the existing template fully
  2. Document the change reasoning in DECISIONS.md
  3. Test with a "dry run" mode that prints the prompt without running Claude
  4. Verify on at least one real project before deploying
  5. Add a version number to the template

When working with the .maestro/ file format

  1. Always validate with Zod before reading
  2. If schema changes, write a migration (parse old format, save in new format)
  3. Never assume the file exists — handle missing gracefully
  4. Lock files during writes (concurrent sessions could corrupt state)

When adding a new quality gate

  1. Add the gate type to packages/shared/src/types.ts
  2. Implement the runner in packages/conductor/src/quality-gates.ts
  3. Default to non-strict (warn, don't fail) until proven reliable
  4. Document the gate in docs/PROMPT_DESIGN.md

Read the full file on GitHub · 112 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. 5d ago First seen · 112 lines · 967 tokens per session scan A 5ee944b25add

Subscribe to this mod's changes

Maestro AGENTS.md is an instructions file published in the GitHub repository aaryansinha16/Maestro (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 967 tokens to every session, about $0.0048 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 2026-08-31.

Related

Other instructions, from other repositories

Opencode-Ultrathinker AGENTS.md

AGENTS.md instructions for Kacper0199/Opencode-Ultrathinker, covering global workspace constitution, 1. language & communication, 2. code standards (no comments rule), 3. persistent memory (macrodata) and 4. git protocol & environment.

Kacper0199/Opencode-Ultrathinker · 1,549 tokens

slipway AGENTS.md

AGENTS.md instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.

signalridge/slipway · 470 tokens

slipway CLAUDE.md

Claude Code instructions for signalridge/slipway: Read AGENTS.md. It is the single principle file for this repository, and it applies to Claude Code exactly as written.

signalridge/slipway · 101 tokens

factory CLAUDE.md

Claude Code instructions for watt-mind/factory: Claude, please refer to AGENTS.md and docs/protocol.md for the primary repository context, architecture, commands, operational rules, and tracker issue management standards.

watt-mind/factory · 77 tokens

RepoResident AGENTS.md

Instructions for ychamel/RepoResident: Agent entry point: read CLAUDE.md in full — it is the operating manual — then follow its Session protocol. Everything else (state, workflows, project knowledge) is routed from there via the .agent/ directory.

ychamel/RepoResident · 50 tokens

factory AGENTS.md

AGENTS.md instructions for watt-mind/factory, covering commands, agent operating floor, handoff, never auto-merge and protected branches.

watt-mind/factory · 6,798 tokens