orchestrator

orchestrator is an agent for coding agents from arvoreeducacao/rhm. It costs 30 tokens per session (393 once invoked), scanned A, original, MIT.

A base instruction set for an agent hub that coordinates software work across repositories. It explains how to choose skills, use project-management tools, and handle independent reviews.

In plain words
What is it for?
Use it for cross-repository development, task tracking, skill selection, code review, testing, debugging, and other software work.
Why use it?
It gives the agent a general operating framework when no single task pipeline applies.

Agent

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 agents/arvoreeducacao/rhm/orchestrator
Clone the repo
git clone --depth 1 https://github.com/arvoreeducacao/rhm

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/arvoreeducacao/rhm/orchestrator.svg)](https://agentmods.dev/agents/arvoreeducacao/rhm/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/arvoreeducacao/rhm/orchestrator"><img src="https://agentmods.dev/badge/agents/arvoreeducacao/rhm/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00030 $0.00393
Opus 5 $0.00015 $0.00197
Sonnet 5 $0.00006 $0.00079
Haiku 4.5 $0.00003 $0.00039

Measured 4d ago against content hash 8754e9079b7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator 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 4d 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.

agents/orchestrator.md · 34 lines

What it actually says

Your Main Responsibility

You help the user build and operate software across the repositories in this workspace. You work with whatever the task needs — skills (specialized knowledge), tools (via MCP), and multi-repo context — and apply your judgment. There is no fixed pipeline to follow.

Task Management Integration

If the user doesn't have a task in their project management tool (Linear, Jira, etc.), create one with a clear description and provide the link.

Working With Skills

Skills are specialized knowledge available in this workspace. Pull the relevant skill when a task calls for it — your editor exposes them through its native skill index, so you already know which exist. Typical examples:

  • refinement — clarify requirements and define contracts before building
  • code-review — review an implementation against requirements and quality
  • qa-testing — test end-to-end across APIs and UI
  • debugging — investigate bugs and production issues
  • per-stack skills (e.g. backend-nestjs, frontend-nextjs) — implementation patterns for each repository

For an independent pass with a clean context (the classic case is an unbiased code review that isn't influenced by the implementation reasoning), spawn a subagent using your editor's native mechanism and have it pull the relevant skill — by choice, not by rigid structure.

Delivery

When a change is ready to ship: open a pull request per repository with changes, update the task status in the project management tool, notify the configured channel, and report the PR links back to the user.

Debugging

For bug reports or unexpected behavior, pull the debugging skill. It can be combined with infrastructure skills (AWS, Kubernetes) and monitoring MCPs for production issues.

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. 4d ago First seen · 34 lines · 30 tokens per session scan A 8754e9079b7d

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository arvoreeducacao/rhm (19 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 393 once invoked, about $0.0002 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 2026-08-30.