orchestrator-auto

orchestrator-auto is a cursor rule for Cursor from FASFG5T5/agent-orchestration. It costs 453 tokens per session, scanned A, original, MIT.

A set of automatic coordination rules for projects where multiple agents work together. It requires agents to register, claim assigned tasks, and check or acquire file locks before editing.

In plain words
What is it for?
Registering agents, claiming tasks, checking whether files are locked, acquiring edit access, and coordinating work across agents.
Why use it?
Without coordination, agents can duplicate work or overwrite each other’s changes. These rules make ownership and editing status explicit.

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/fasfg5t5/agent-orchestration/orchestrator-auto
Clone the repo
git clone --depth 1 https://github.com/FASFG5T5/agent-orchestration

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 orchestrator-auto

README.md
[![agentmods](https://agentmods.dev/badge/rules/fasfg5t5/agent-orchestration/orchestrator-auto.svg)](https://agentmods.dev/rules/fasfg5t5/agent-orchestration/orchestrator-auto)
Your own site
<a href="https://agentmods.dev/rules/fasfg5t5/agent-orchestration/orchestrator-auto"><img src="https://agentmods.dev/badge/rules/fasfg5t5/agent-orchestration/orchestrator-auto.svg" alt="Measured on agentmods" height="20"></a>
Per session 453 This file is loaded in full into every session.
When invoked 453 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 $0.00453 $0.00453
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 5d ago against content hash 5c63feb36798, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

orchestrator-auto 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.

.cursor/rules/orchestrator-auto.mdc · 108 lines

What it actually says

CRITICAL: MULTI-AGENT COORDINATION ACTIVE

This project uses Agent Orchestration. You MUST follow these rules.


⚠️ MANDATORY FIRST ACTION ⚠️

BEFORE doing ANYTHING else, you MUST run this tool:

bootstrap

This registers you with the orchestrator and shows you:

  • Current project focus
  • Tasks assigned to you
  • Recent decisions

DO NOT skip this step. DO NOT start coding before running bootstrap.


If You Were Spawned With a Todo/Task

If you were given a specific task or todo when you started (e.g., via "Build in New Agent"):

Run this IMMEDIATELY:

claim_todo:
  title: "<the todo/task title you were given>"

This will:

  1. Register you as an agent
  2. Create or find the matching task
  3. Claim it so other agents know you're working on it

Example: If you were spawned with "Create .env.example for environment variables", run:

claim_todo:
  title: "Create .env.example for environment variables"

Before Any File Edit

  1. Check if the file is locked:

    lock_check:
      resource: "<file_path>"
    
  2. If not locked, acquire a lock:

    lock_acquire:
      resource: "<file_path>"
      reason: "<what you're doing>"
    
  3. Release when done.


Check Before Major Work

is_my_turn

If "No" - wait or check what tasks are available:

task_list:
  status: "pending"

Reference activeContext.md

Check activeContext.md for current project state - it's auto-updated.


When Done With Your Task

task_complete:
  task_id: "<your_task_id>"
  output: "<summary of what you did>"

On Session End

agent_unregister
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 · 108 lines · 453 tokens per session scan A 5c63feb36798

Subscribe to this mod's changes

orchestrator-auto is a cursor rule published in the GitHub repository FASFG5T5/agent-orchestration (1 stars, last pushed yesterday), licensed MIT. It adds 453 tokens to every session, about $0.0023 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.