langgraph-designer

langgraph-designer is a skill for Claude Code, Codex from khalilbenaz/claude-skills-collection. It costs 103 tokens per session (2,612 once invoked), scanned A, original, MIT.

A guide for designing complex, stateful agent workflows with LangGraph, a Python framework for connecting steps, branches, and loops.

In plain words
What is it for?
Use it to define shared workflow state, connect agent steps, add branches and cycles, save progress between runs, and pause for human review.
Why use it?
It helps manage workflows that need saved progress, conditional paths, retries, human approval, or coordination between specialized agents.

Skill for Claude CodeCodex

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

Good fit Use it to define shared workflow state, connect agent steps, add branches and cycles, save progress between runs, and pause for human review.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/langgraph-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/langgraph-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,612 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 $0.00103 $0.02612
Opus 5 $0.00051 $0.01306
Sonnet 5 $0.00021 $0.00522
Haiku 4.5 $0.00010 $0.00261

Measured 11d ago against content hash 9e5d19df4a2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

langgraph-designer 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 11d 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/langgraph-designer/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LangGraph Designer — Graphes d'Agents Stateful

Quand utiliser ce skill

LangGraph est pertinent quand au moins une de ces conditions est vraie :

  • Le workflow n'est pas linéaire (branches, cycles, retry)
  • L'état doit persister entre plusieurs appels ou sessions
  • Une validation humaine doit interrompre l'exécution
  • Plusieurs agents spécialisés doivent se coordonner

Alternatives : LangChain LCEL pour les pipelines linéaires simples, CrewAI si tu veux une abstraction haut niveau sans gérer le state manuellement.


Workflow en étapes

1. Installation et imports

pip install langgraph>=0.3.0 langchain-openai>=0.2.0
# Persistance PostgreSQL (prod) :
pip install langgraph-checkpoint-postgres psycopg[binary]
from langgraph.graph import StateGraph, START, END
from langgraph.prebuilt import ToolNode, tools_condition
from langgraph.checkpoint.memory import MemorySaver
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage, BaseMessage
from typing import TypedDict, Annotated
import operator

2. Définir le State (TypedDict)

Le State est le schéma partagé entre tous les nœuds. Règle critique : toujours annoter les listes avec un reducer.

from langgraph.graph.message import add_messages  # reducer officiel pour messages

class AgentState(TypedDict):
    messages: Annotated[list[BaseMessage], add_messages]  # append, déduplique par id
    iteration_count: int        # compteur anti-boucle infinie
    final_answer: str | None

Critères de choix du reducer :

Besoin Reducer
Accumuler des messages add_messages
Accumuler une liste générique operator.add
Remplacer la valeur Aucun (défaut)
Valeur max/min lambda a, b: max(a, b)

Raccourci pour chatbots purs : from langgraph.graph import MessagesState (hérite déjà de add_messages).

3. Créer les nœuds

Un nœud est une fonction pure : reçoit le state complet, retourne un dict partiel (seules les clés modifiées).

Read the full file on GitHub · 292 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. 11d ago First seen · 292 lines · 103 tokens per session scan A 9e5d19df4a2b

Subscribe to this mod's changes

langgraph-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 2,612 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 2026-08-30.