pipeline-composer

pipeline-composer is a skill for Claude Code, Codex from khalilbenaz/claude-skills-collection. It costs 84 tokens per session (2,734 once invoked), scanned A, original, MIT.

A guide for linking software agents into a workflow where one agent's result becomes the next agent's input.

In plain words
What is it for?
Use it for data extraction and loading, content production, lead qualification, or document processing with sequential, branching, or parallel stages.
Why use it?
It makes complex work easier to divide into dependent steps and clarifies when steps can run at the same time.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for data extraction and loading, content production, lead qualification, or document processing with sequential, branching, or parallel stages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khalilbenaz/claude-skills-collection/pipeline-composer
Install

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.

Any agent
npx skills add khalilbenaz/claude-skills-collection --skill pipeline-composer
Clone the repo
git clone --depth 1 https://github.com/khalilbenaz/claude-skills-collection

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pipeline-composer

README.md
[![agentmods](https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/pipeline-composer/github.svg)](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/pipeline-composer)
Your own site
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/pipeline-composer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/pipeline-composer/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.

agentmods 80×15 button for pipeline-composer

Your own site · 80×15
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/pipeline-composer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/pipeline-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.02734
Opus 5 $0.00042 $0.01367
Sonnet 5 $0.00017 $0.00547
Haiku 4.5 $0.00008 $0.00273

Measured 12d ago against content hash fd6ce1c4ee5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pipeline-composer 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 12d 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.

agent-skills/pipeline-composer/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Pipeline Composer

Quand utiliser ce skill

Ce skill est adapté lorsqu'une tâche complexe doit être décomposée en étapes séquentielles ou parallèles, chaque étape étant assurée par un sous-agent spécialisé dont le résultat alimente directement l'étape suivante.

Cas d'usage typiques :

  • Pipelines ETL : Extract (scraping/API) → Transform (parsing/enrichissement) → Load (DB/fichier)
  • Traitement de contenu : Recherche → Analyse → Rédaction → Révision → Publication
  • Qualification de leads : Enrichissement → Scoring → Segmentation → Routage CRM
  • Traitement de documents : OCR → NLP → Extraction → Validation → Stockage

Ne pas utiliser si : les étapes n'ont pas de dépendances de données entre elles (utiliser un pool d'agents parallèles indépendants à la place).


Étapes de conception

1. Choisir la topologie

Topologie Quand l'utiliser Structure
linear Étapes strictement séquentielles, chaque output = input du suivant A → B → C
DAG Dépendances multiples, parallélisme possible A → (B ‖ C) → D
conditional branch Routing selon le résultat d'une étape A → if X then B else C
map-reduce Même traitement sur N items, puis agrégation A → [B₁‖B₂‖B₃] → C
loop Itérer jusqu'à un critère de satisfaction (qualité, score) A → B → if OK then fin else A

2. Définir les schémas d'interface

Chaque stage doit avoir un contrat explicite. C'est la source n°1 de bugs quand il est flou.

from pydantic import BaseModel

class ResearchOutput(BaseModel):
    raw_text: str
    sources: list[str]
    confidence: float  # 0.0 – 1.0

class AnalysisInput(BaseModel):
    raw_text: str       # mappé depuis ResearchOutput.raw_text
    sources: list[str]  # mappé depuis ResearchOutput.sources

class AnalysisOutput(BaseModel):
    summary: str
    key_points: list[str]
    confidence: float

Valider à chaque frontière entre stages (model.model_validate(output_dict)) — erreur de parsing = bug de mapping attrapé immédiatement, pas deux stages plus loin.

Read the full file on GitHub · 264 lines

Changes

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.

  1. 12d ago First seen · 264 lines · 84 tokens per session scan A fd6ce1c4ee5f

Subscribe to this mod's changes

pipeline-composer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 84 tokens to every session and 2,734 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 2026-08-30.