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 khalilbenaz/claude-skills-collection --skill ai-workflow-orchestratorgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/ai-workflow-orchestrator)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/ai-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/ai-workflow-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/khalilbenaz/claude-skills-collection/ai-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/ai-workflow-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.02306 |
| Opus 5 | $0.00039 | $0.01153 |
| Sonnet 5 | $0.00015 | $0.00461 |
| Haiku 4.5 | $0.00008 | $0.00231 |
Grade A, and why
ai-workflow-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 8d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Workflow Orchestrator
Critères de décision : quel framework choisir ?
| Complexité | Pattern | Framework recommandé |
|---|---|---|
| 1–3 étapes linéaires | Séquentiel simple | Python natif ou LCEL |
| Fan-out / fan-in sans état | Parallèle sans mémoire | LCEL RunnableParallel |
| Boucles, conditions, état persistant | Agent / cycle | LangGraph |
| RAG + retrieval hybride | Search pipeline | Haystack |
| Stack Azure / .NET | Intégration Microsoft | Semantic Kernel |
| Contrôle total, zéro dépendance | Custom | Script async pur |
Règle d'or : n'ajouter un framework que quand la complexité le justifie. 50 lignes de Python natif > architecture LangGraph mal comprise.
Workflow en étapes
1. Décomposer en DAG avant de coder
Identifier pour chaque étape : input attendu, output produit, dépendances. Dessiner un DAG — économise des heures de débogage.
Pipeline d'analyse de document :
[Chargement] → [Extraction] ─┬─ [Résumé] ─┐
├─ [Entités NER] ├─ [Rapport final]
└─ [Sentiment] ─┘
Questions à poser : quelles étapes sont indépendantes (candidats au parallélisme) ? Quelles étapes nécessitent un état partagé ? Y a-t-il des points de décision conditionnels ?
2. Implémenter les patterns de chaînes
Séquentiel (LCEL | operator)
from langchain_core.runnables import RunnableLambda
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o-mini")
pipeline = extract_prompt | llm | parse_output | report_prompt | llm
result = pipeline.invoke({"document": text})
Parallèle (fan-out / fan-in)
from langchain_core.runnables import RunnableParallel
parallel = RunnableParallel({
"summary": summarize_prompt | llm,
"entities": extract_prompt | llm,
"sentiment": sentiment_prompt | llm,
})
full = parallel | merge_results | report_prompt | llm
result = full.invoke({"document": text})
Map-Reduce (N documents)
from langchain_core.runnables import RunnableLambda
import asyncio
async def map_reduce(docs: list[str]) -> str:
summaries = await asyncio.gather(*[
summarize_chain.ainvoke({"text": d}) for d in docs
])
return await aggregate_chain.ainvoke({"summaries": summaries})
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.
- 8d ago First seen · 269 lines · 77 tokens per session scan A bf3c588e106a
ai-workflow-orchestrator is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 77 tokens to every session and 2,306 once invoked, about $0.0004 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
json-mode-patterns
Structured JSON output from Claude: tool-use-as-JSON, schema, parsing, partial recovery. Triggers: JSON mode, structured output, schema validation, JSON parsing.
model-strategy
Multi-model orchestration and model-switching strategy. Score-based model selection, reasoning-effort routing, cross-agent delegation (Gemini, Codex, Ollama), advisor pairing, escalation triggers, permission matrix, and cost-efficiency optimization.
creator-prompt-engineer
Convert creative-department outputs (script, vision, cinematography, characters, sets, storyboards, shots) into producible, consistent AI image/video prompts — with tool-specific optimization, locked anchors, negative prompts, and safe alternatives. Default image tool priority for storyboard/character sheets is GPT…
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
prompt-engineer
Use this skill when the user explicitly asks to create, write, improve, or optimize a prompt for use with an AI. Trigger on phrases like "write me a prompt", "improve this prompt", "create a system prompt", "how do I ask ChatGPT/Claude to...", or "quero um prompt para...". Do NOT trigger for direct task requests where…
midjourney-prompter
Engineer Midjourney prompts — style references, aspect ratios, negative prompts, and v6 parameter tuning.