maestro-dispatch

maestro-dispatch is a cursor rule for Cursor from pjasielski/maestro. It costs 512 tokens per session, scanned A, original, MIT.

A command dispatcher for Maestro, a project workflow tool, that matches chat commands to instruction files in the .maestro/commands/ folder.

In plain words
What is it for?
It is for handling commands such as exploring, planning, implementing, reviewing, initializing, syncing, and checking project status.
Why use it?
It removes the need to manually find and load the right instruction file for each Maestro command.

Cursor rule for Cursor

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 rules/pjasielski/maestro/maestro-dispatch
Clone the repo
git clone --depth 1 https://github.com/pjasielski/maestro

Made for: Cursor.

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-dispatch

README.md
[![agentmods](https://agentmods.dev/badge/rules/pjasielski/maestro/maestro-dispatch.svg)](https://agentmods.dev/rules/pjasielski/maestro/maestro-dispatch)
Your own site
<a href="https://agentmods.dev/rules/pjasielski/maestro/maestro-dispatch"><img src="https://agentmods.dev/badge/rules/pjasielski/maestro/maestro-dispatch.svg" alt="Measured on agentmods" height="20"></a>
Per session 512 This file is loaded in full into every session.
When invoked 512 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 $0.00512 $0.00512
Opus 5 $0.00256 $0.00256
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 3d ago against content hash 4aa411717c1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maestro-dispatch 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 3d 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.

.cursor/rules/maestro-dispatch.mdc · 51 lines

What it actually says

Maestro Command Dispatch

When the user types a Maestro command in chat, load and follow the corresponding command file from .maestro/commands/.

Command Recognition

Recognize these patterns (with or without / prefix):

User types Load file
mae-explore or mex .maestro/commands/mae-explore.md
mae-poc or mpoc .maestro/commands/mae-poc.md
mae-req or mrq .maestro/commands/mae-req.md
mae-design or mds .maestro/commands/mae-design.md
mae-plan or mpl .maestro/commands/mae-plan.md
mae-do or mdo .maestro/commands/mae-do.md
mae-review or mrv .maestro/commands/mae-review.md
mae-init .maestro/commands/mae-init.md
sync .maestro/commands/sync.md
decide .maestro/commands/decide.md
status .maestro/commands/status.md
md .maestro/commands/md.md

Dispatch Protocol

  1. When a command is recognized, read the full command file from .maestro/commands/
  2. Pass any arguments the user provided after the command name
  3. Follow the command file's behavior specification exactly
  4. Save output to the current session folder as specified

Examples

User: "mae-explore the auth system"
→ Read .maestro/commands/mae-explore.md
→ Execute with argument: "the auth system"

User: "mex ask client"
→ Read .maestro/commands/mae-explore.md
→ Execute with arguments: "ask client"

User: "mrq"
→ Read .maestro/commands/mae-req.md
→ Execute with no arguments (smart default)

If unsure whether input is a command: if the first word matches a command name above, treat it as a command. Otherwise treat it as a regular message.

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. 3d ago First seen · 51 lines · 512 tokens per session scan A 4aa411717c1a

Subscribe to this mod's changes

maestro-dispatch is a cursor rule published in the GitHub repository pjasielski/maestro (4 stars, last pushed 22d ago), licensed MIT. It adds 512 tokens to every session, about $0.0026 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.