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 pipeline-optimizergit 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/pipeline-optimizer)<a href="https://agentmods.dev/skills/ellmos-ai/skills/pipeline-optimizer"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/pipeline-optimizer/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/pipeline-optimizer"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/pipeline-optimizer.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 | $0.00189 | $0.04299 |
| Opus 5 | $0.00095 | $0.02150 |
| Sonnet 5 | $0.00038 | $0.00860 |
| Haiku 4.5 | $0.00019 | $0.00430 |
Grade A, and why
pipeline-optimizer 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 9d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline-Optimizer / Projekt-Ordner-Optimizer
6-Schritte-Renovierung ohne Inkompatibilitäten — anwendbar auf zwei Größenordnungen:
| Trigger-Name | Anwendungsbereich | Beispiel |
|---|---|---|
| Pipeline-Optimizer | Ganze Pipelines, Stacks, Doku-Strukturen | Deine Themen-Pipelines, z.B. software/, research/, games/, ein Agenten-System |
| Projekt-Ordner-Optimizer | Einzelne Projektordner innerhalb einer Pipeline | Ein Software-Tool, ein Paper-Projekt, ein Game-Projekt |
Eine Pipeline meint hier eine themenbezogene Top-Level-Struktur, in der mehrere Projekte nach gemeinsamen Konventionen leben (z.B. eine Software-Pipeline mit Release-Regeln, eine Forschungs-Pipeline mit Publikationsverfahren).
Beide nutzen denselben 6-Schritte-Workflow — der Unterschied liegt nur im Scope (Pipeline-weit vs. Einzelprojekt) und entsprechend in der Tiefe der Bausubstanz-Erfassung in Schritt A.
Wann dieser Skill greift
Der Skill greift, sobald du eine bestehende Struktur verbessern, umbauen oder erweitern sollst — nicht beim Greenfield-Bau. Konkrete Trigger:
Pipeline-Ebene (Scope: ganze Pipeline):
- „Pipeline X besser machen"
- „Stack optimieren"
- „Renovierung der Software-Pipeline"
- „Doku-Konsolidierung in der Forschungs-Pipeline"
- Substantieller Eingriff in eine Themen-Pipeline, zentrale
_tools/oder System-Komponenten
Projektordner-Ebene (Scope: einzelner Projektordner):
- „Projektordner X aufräumen/optimieren"
- „Ordnerstruktur in Y verbessern"
- „Einzelnes Tool refactorieren"
- „Paper-Projekt-Setup vereinheitlichen"
- „Game-Projektordner an Pipeline-Standard anpassen"
Übergreifend:
- „X umbauen/integrieren in bestehendes Y"
- „Refactoring", „Konsolidierung"
- „Konventionen vereinheitlichen"
- „in bestehendes System integrieren"
Die Bausubstanz-Metapher
Ein Haus zu renovieren erfordert zuerst zu wissen, aus was es besteht (Steine, Holz, Plastik), wofür es da ist (Berghütte, Softwareschmiede), und wo es jetzt schon Funktionen erfüllt. Dieselbe Disziplin gilt für Pipelines.
What ships with it
13 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.
- 9d ago First seen · 297 lines · 189 tokens per session scan A d7951e69f299
pipeline-optimizer is a skill published in the GitHub repository ellmos-ai/skills (4 stars, last pushed yesterday), licensed MIT. It adds 189 tokens to every session and 4,299 once invoked, about $0.0009 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
accelerate
Run PyTorch training across GPUs with minimal changes.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
conference-report
Use when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help building (1) faithful per-session reconstructions in markdown (slide visuals + speaker transcript with Whisper hallucination annotations), and (2) a downstream report deliverable whose scope and format…
ctf-kit
Use when the user is solving an authorized CTF / lab reverse-engineering challenge focused on Windows application authentication or license-check bypass. Guides triage → static analysis → dynamic experiment planning → bypass verification, with strong evidence discipline and VM safety boundaries. NOT for real-world…
md2pdf
Use when the user wants to convert one Markdown file into a publication-ready A4 PDF, especially when the source may contain Mermaid diagrams, ASCII diagrams, CJK text, tables, or pandoc/weasyprint edge cases. Works by copying the source to a pdf.md working file, converting diagrams, escaping PDF-breaking syntax…