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 skills add ellmos-ai/skills --skill choose-your-orchestratorgit clone --depth 1 https://github.com/ellmos-ai/skillsWrote 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/skills/ellmos-ai/skills/choose-your-orchestrator)<a href="https://agentmods.dev/skills/ellmos-ai/skills/choose-your-orchestrator"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/choose-your-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/skills/ellmos-ai/skills/choose-your-orchestrator"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/choose-your-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 | $0.00105 | $0.02095 |
| Opus 5 | $0.00053 | $0.01047 |
| Sonnet 5 | $0.00021 | $0.00419 |
| Haiku 4.5 | $0.00011 | $0.00210 |
Grade A, and why
choose-your-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 2d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choose Your Orchestrator
Zweck
Kläre vor komplexer Multi-Agent-Arbeit die Randbedingungen, empfehle die kleinste wirksame Kombination vorhandener Skills und gib einen verbindlichen Session-Orchestrierungsvertrag aus. Lade die ausgewählten Skills über den Skill-Mechanismus der aktuellen Runtime und folge ihren Live-Anleitungen. Kopiere ihre Verfahren nicht in diesen Skill.
Delegation erweitert niemals die Autorität. Externe oder irreversible Aktionen wie Veröffentlichen, Senden, Löschen, Bezahlen oder produktive Änderungen bleiben beim Nutzer gegatet, sofern der aktuelle Auftrag sie nicht ausdrücklich autorisiert.
Bausteine
| Baustein | Aufgabe im Vertrag | Nicht seine Aufgabe |
|---|---|---|
orchestrator |
Arbeitspakete, Scopes, Evidenz und Abnahme | Modellwahl oder Schwarmmuster erfinden |
swarm-operations |
Schwarmmuster, Kosten-Gate und optionale Matruschka-Staffelung | Einzelaufgaben künstlich parallelisieren |
model-strategy |
Fähigkeits- und modellbezogene Route anhand der Live-Verfügbarkeit | feste Modellversionen oder Berechtigungen vorgeben |
clutch |
optionaler externer Routingvorschlag | alleinige Autorität für Dispatch oder Scope |
decision-avatar |
optionales autorisiertes Präferenzsignal bei reversiblen Unsicherheiten | Nutzerfreigaben ersetzen oder Autorität erweitern |
Nutze clutch route "<kurze Aufgabenbeschreibung>" --json nur, wenn clutch
tatsächlich verfügbar ist. Behandle die JSON-Antwort als Vorschlag und gleiche sie
gegen verfügbare Runtime-Slots, Budget, Projektregeln und Nutzergrenzen ab. Ist
clutch nicht verfügbar oder seine Ausgabe unlesbar, nutze model-strategy und
die Live-Fähigkeiten der Runtime. Hardcode keine aktuellen Modellnamen oder
-versionen in den Vertrag.
Empfehlungsdialog
1. Aufgabe einordnen
Ermittle Ziel, Aufgabentyp, Erfolgskriterien, negative Scopes, aktuelle Berechtigungen, vorhandene Locks und unabhängige Arbeitspakete. Wähle zunächst den kleinsten passenden Routenvorschlag aus der Tabelle unten.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +2 lines 0b9927041d35
- 8d ago First seen · 187 lines · 105 tokens per session scan A 8e96b150e036
choose-your-orchestrator is a skill published in the GitHub repository ellmos-ai/skills (4 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 2,095 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.