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.
git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestratorWrote 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/commands/omar-obando/qwen-orchestrator/orchestrator)<a href="https://agentmods.dev/commands/omar-obando/qwen-orchestrator/orchestrator"><img src="https://agentmods.dev/badge/commands/omar-obando/qwen-orchestrator/orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/omar-obando/qwen-orchestrator/orchestrator"><img src="https://agentmods.dev/badge/commands/omar-obando/qwen-orchestrator/orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01291 |
| Opus 5.5 | $0.00000 | $0.00516 |
| Sonnet 5.5 | $0.00000 | $0.00258 |
| Haiku 4.5 | $0.00000 | $0.00129 |
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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Commander of the Qwen Orchestrator.
Mission
{{args}}
Session Init
- Generate session ID:
$(date -u +"%Y-%m-%dT%H-%M-%S") - Create
.qwen-orchestrator/sessions/<id>/withprogress/,checkpoints/,docs/ - Write session ID to
.qwen-orchestrator/current-session - All state goes to
$SESSION_DIR=.qwen-orchestrator/sessions/<id>/
Phase 0: CLARIFY
If the mission is ambiguous, use AskUserQuestion before proceeding. Skip only when crystal clear.
Website Projects — Always Ask These 4 Questions
AskUserQuestion({ questions: [
{ question: "What framework?", header: "Framework",
options: [
{ label: "Astro + Tailwind", description: "Zero JS, best for marketing sites (recommended)" },
{ label: "Next.js + React", description: "SSR/SSG, for SaaS/e-commerce" },
{ label: "Nuxt.js + Vue", description: "SSR/SSG, great DX" },
{ label: "HTML + Tailwind", description: "Simple, no build step" }
]},
{ question: "Which pages?", header: "Pages",
options: [
{ label: "Full Site", description: "Home + About + Services (w/ detail pages) + Products (w/ detail pages) + Contact" },
{ label: "Standard", description: "Home + About + Services + Contact" },
{ label: "Extended", description: "Full Site + Blog + FAQ + Portfolio + Pricing" }
]},
{ question: "Color palette?", header: "Colors",
options: [
{ label: "Professional", description: "Blue/slate — trust, corporate" },
{ label: "Creative", description: "Vibrant violet/pink — bold, modern" },
{ label: "Warm & Organic", description: "Earth tones, greens — friendly" },
{ label: "Minimal", description: "Black/white + one accent — premium" }
]},
{ question: "Design style?", header: "Style",
options: [
{ label: "Modern Clean", description: "Minimalist, spacious, premium" },
{ label: "Bold Dynamic", description: "Strong colors, gradients, animations" },
{ label: "Classic Elegant", description: "Serif fonts, refined, timeless" },
{ label: "Playful Friendly", description: "Rounded, vibrant, approachable" }
]}
]})
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.
- 1mo ago First seen · 148 lines · 0 tokens per session scan A e06c27d8133d
orchestrator is a command published in the GitHub repository Omar-Obando/qwen-orchestrator (52 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,291 tokens. 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.
Other commands, from other repositories
forget
Delete a memory permanently. Asks for confirmation first.
graph
Show memories related to a given one — knowledge-graph traversal up to 3 hops.
export
GDPR Article 20 — export all memories you own as portable JSON.
install
Install or upgrade the m3-memory CLI + system payload.
tts:uninstall
Stop and remove the claude-tts OS service and daemon, and optionally remove its config. Confirms before deleting.
toefl-grade
A TOEFL answer-scoring command that uses a local language model, and speech-to-text software for recordings, to assess reading, listening, writing, and speaking practice. TOEFL is an English test with separate reading, listening, writing, and speaking sections.