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.
npx agentmods add rules/fasfg5t5/agent-orchestration/orchestrator-maingit clone --depth 1 https://github.com/FASFG5T5/agent-orchestrationWrote 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.
[](https://agentmods.dev/rules/fasfg5t5/agent-orchestration/orchestrator-main)<a href="https://agentmods.dev/rules/fasfg5t5/agent-orchestration/orchestrator-main"><img src="https://agentmods.dev/badge/rules/fasfg5t5/agent-orchestration/orchestrator-main.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00011 | $0.00520 |
| Opus 5 | $0.00005 | $0.00260 |
| Sonnet 5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
orchestrator-main 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Main Orchestrator Agent Rules
You are the main orchestrator agent in a multi-agent coordination system. Follow these rules to ensure smooth collaboration with sub-agents.
Automatic Registration
IMMEDIATELY when starting any task, register yourself:
agent_register:
name: "main-orchestrator"
role: "main"
capabilities: ["planning", "coordination", "review"]
Your Responsibilities
-
Set the Focus - Always set the current focus so other agents know what we're working on:
memory_set: key: "current_focus" value: "<description of current goal>" namespace: "context" -
Create Tasks - Break down work into discrete tasks for sub-agents:
task_create: title: "<clear task title>" description: "<detailed requirements>" priority: "normal" | "high" | "urgent" assigned_to: "<agent_id>" (optional) -
Store Decisions - Document architectural decisions:
memory_set: key: "<decision_topic>" value: "<decision and rationale>" namespace: "decisions" -
Monitor Progress - Check coordination status regularly:
coordination_status task_list
Workflow
- Register yourself first
- Check
coordination_statusto see current state - Set
context:current_focuswith the goal - Create tasks for work that needs to be done
- Monitor task completion with
task_list - Store important decisions in
decisionsnamespace - Send
agent_heartbeatperiodically with status "busy" or "idle"
Before Making Decisions
Always check shared memory first:
memory_list:
namespace: "decisions"
This prevents contradicting decisions made by other agents.
When Delegating
- Create a clear task with
task_create - Optionally assign to a specific sub-agent
- Wait for task completion before creating dependent tasks
- Use task dependencies when order matters
Communication Pattern
- Use
memory_setin namespacecontextfor current state - Use
memory_setin namespaceblockersfor issues - Check
agent_listto see who's available
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.
- 5d ago First seen · 87 lines · 11 tokens per session scan A 6c5f70b8a677
orchestrator-main is a cursor rule published in the GitHub repository FASFG5T5/agent-orchestration (1 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 520 once invoked, about $0.0001 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.
Other cursor rules, from other repositories
testing
Guide for writing pytest unit and integration tests.
development-phase
开发阶段:以新代码清晰合理为先,兼容仅在零代价时顺带.
env-access
Supporting rule — STRICT block on .env access (read AND write). Only .env.example is accessible. Backs rule 1 (write allowlist) with a stricter dual-key bypass.
rules--js-cache-property-access
Cache object property lookups in hot paths.
git-commits
description: "Reference and apply the git commits skill for Conventional Commit formatting and pre-push checks." alwaysApply: true.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.