maestro: Instructions file for Codex

AGENTS.md

maestro AGENTS.md is an instructions file for Codex, OpenCode from ReinaMacCredy/maestro. It costs 484 tokens per session, scanned A, original, MIT.

Project instructions for Maestro, a TypeScript program that runs on Bun, a JavaScript runtime. They describe its code layout, work records, development method, and repository rules.

In plain words
What is it for?
Use them when developing Maestro, including choosing the right work record, editing bundles, running tests, and following its Bun-based toolchain.
Why use it?
They give a coding agent the project context it needs before changing files. This reduces mistakes such as using the retired Rust setup or putting code in the wrong area.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is ReinaMacCredy/maestro's own configuration. It tells Codex and OpenCode how to work on maestro itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything maestro configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ReinaMacCredy/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/ReinaMacCredy/maestro/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ReinaMacCredy/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/reinamaccredy/maestro/agents-md.svg)](https://agentmods.dev/instructions/reinamaccredy/maestro/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/reinamaccredy/maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/reinamaccredy/maestro/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 484 This file is loaded in full into every session.
When invoked 484 The same file — it is already loaded in full.
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 $0.00484 $0.00484
Opus 5 $0.00242 $0.00242
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00048 $0.00048

Measured 2d ago against content hash ba869aff1d71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

maestro AGENTS.md 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 2d 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.

`scripts/install.sh` is the curl installer; `site/` is the Starlight docs site
AGENTS.md · 34 lines

What it actually says

maestro

TypeScript on Bun since v0.108.0 (0.107.x was the Rust line, whose stores are preserved under legacy/rust/). Work happens on main; the rewrite-maestro-in-typescript branch and the .maestro/worktree/rewrite-ts worktree are retired.

Layout: src/kernel/ is mechanism only (store, event log, sessions, cli, loader); src/plugins/ holds verbs and policies; src/plugins/recipes/ and src/plugins/skills/ are prompt-first markdown; bin/maestro.ts is the entry; scripts/install.sh is the curl installer; site/ is the Starlight docs site published by .github/workflows/pages.yml; tests/ is bun:test.

Method: maestro recipe show work for depth, ~/maestro/skills/maestro-bundle for the tier rule (quickfix: a one-sentence diff with no Full trigger, done directly with inline verification and no record; Light: a work item; Full: a bundle). Bundles live in .maestro/bundle/<id>/ (SPEC/NOTES/VERIFY); NOTES.md is an overwrite-only handoff, and history lives in the store (maestro work note, maestro trace, decisions), never in the file.

Rules:

  • Toolchain: bun only (runtime, bun:sqlite, bun:test). Install from a checkout with bun bin/maestro.ts install; maestro update follows that checkout, fast-forward only.
  • Kernel stays free of policy vocabulary (CI gate A2); no daemon, scheduler, or detached process (A1); no escape-hatch flags such as lean or --lane light (A3). Run bun test, bunx tsc --noEmit, and those greps before pushing.
  • Test-first: red test, minimal change, green; the full suite runs after install, from the checkout being installed.
  • Never hand-edit the .claude/ and .codex/ wiring; the installer owns those files.
  • Commit per verified step; never push, tag, or release unasked.
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. 2d ago Changed · -11 tokens per session ba869aff1d71
  2. 3d ago Changed · -8 lines · -228 tokens per session 3f97ff883742
  3. 8d ago First seen · 42 lines · 723 tokens per session scan A ac2817ad9e06

Subscribe to this mod's changes

maestro AGENTS.md is an instructions file published in the GitHub repository ReinaMacCredy/maestro (231 stars, last pushed 2d ago), licensed MIT. It adds 484 tokens to every session, about $0.0024 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens