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 rotation-checkgit 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/rotation-check)<a href="https://agentmods.dev/skills/ellmos-ai/skills/rotation-check"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/rotation-check/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/rotation-check"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/rotation-check.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 | $0.00148 | $0.01946 |
| Opus 5 | $0.00074 | $0.00973 |
| Sonnet 5 | $0.00030 | $0.00389 |
| Haiku 4.5 | $0.00015 | $0.00195 |
Grade A, and why
rotation-check 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 10d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zweck
Wer eine Pipeline mit vielen Projekten periodisch prüfen will (Quellen, Stil, Gesundheit, Sicherheit, Übersetzungen, …), steht vor einem Verteilungsproblem: Alle Projekte pro Lauf zu prüfen ist zu teuer; ohne Gedächtnis prüft jeder Lauf zufällig dasselbe. Das Rotations-Muster löst beides: genau ein Ziel pro Lauf, Auswahl nach „am längsten ungeprüft", Registry als Gedächtnis. So deckt auch ein seltener Takt (täglich/wöchentlich) über Wochen die ganze Pipeline ab — nachweisbar und ohne Doppelarbeit.
Bewährt als Rückgrat eines gewachsenen Bestands produktiver Automationen über mehrere Projekt-Pipelines hinweg.
Bausteine
1. Zwei Dateien pro Pipeline (einmalig anlegen)
| Datei | Inhalt | Charakter |
|---|---|---|
CHECKED-REGISTRY.md |
eine Kompaktzeile pro Check: Ziel, Datum, Checktyp, Ergebnis, nächster Schritt | Zustandsübersicht — wird VOR jeder Zielauswahl gelesen |
CHECKS-LOG.txt |
kurzer Verlaufseintrag pro Lauf mit Details/Evidenz | Journal — append-only |
Beide liegen im Pipeline-Root (nicht im Einzelprojekt), damit ein Lauf sie mit einem Read erfassen kann. Registry-Zeilenformat:
| <ziel> | <YYYY-MM-DD> | <checktyp> | <ok|befund|übersprungen> | <nächster schritt> |
2. Auswahlregel
- Registry und Log lesen (Pflicht, VOR der Auswahl — sonst Doppelprüfung).
- Kandidaten: Ziele, die für DIESEN Checktyp noch nie oder am längsten nicht geprüft wurden.
- Ausweichen, wenn das Ziel kürzlich von einem eng verwandten Check angefasst wurde (z. B. Zitations-Check direkt nach Quellencheck bringt nichts) oder gerade gesperrt/in Bearbeitung ist (Locks respektieren). Geschwister-Cooldown: Laufen mehrere verwandte Checks über dieselbe Zielmenge (z. B. Entwicklung, Bugsuche und Review derselben Pipeline), eine Karenzzeit vereinbaren (Erfahrungswert: ~24 h), in der ein von einem Geschwister-Check bearbeitetes Ziel nicht erneut gewählt wird — verhindert Kollisionen und widersprüchliche Parallel-Änderungen.
- Vorziehen außer der Reihe nur mit gutem Grund (z. B. große Überarbeitung seit letztem Check) — den Grund im Log nennen.
What ships with it
6 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.
- 10d ago First seen · 165 lines · 148 tokens per session scan A b723f4d12040
rotation-check is a skill published in the GitHub repository ellmos-ai/skills (4 stars, last pushed yesterday), licensed MIT. It adds 148 tokens to every session and 1,946 once invoked, about $0.0007 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 skills, from other repositories
token-optimizer
Reduce Claude Code token consumption and API costs without sacrificing output quality. Use this skill whenever the user mentions high costs, expensive sessions, token waste, burning through credits, wanting to use Haiku instead of Opus, model routing, MAXTHINKINGTOKENS, extended thinking cost, CLAUDECODESUBAGENTMODEL…
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".