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-autogit 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-auto)<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>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 | $0.00453 | $0.00453 |
| Opus 5 | $0.00227 | $0.00227 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00045 | $0.00045 |
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.
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:
- Register you as an agent
- Create or find the matching task
- 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
-
Check if the file is locked:
lock_check: resource: "<file_path>" -
If not locked, acquire a lock:
lock_acquire: resource: "<file_path>" reason: "<what you're doing>" -
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
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 · 108 lines · 453 tokens per session scan A 5c63feb36798
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.
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.