parallel-execution-in-langgraph

Guidance for running multiple steps at the same time in LangGraph, a framework for building workflows from connected processing steps.

In plain words
What is it for?
Use it for parallel nodes, fan-out and fan-in workflows, concurrent execution, supersteps, state reducers, the Send API, and deferred nodes.
Why use it?
It helps structure workflows that split into several branches and then combine their results correctly.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/postindustria-tech/agentic-toolkit/langgraph-dev-parallel-execution
Any agent
npx skills add postindustria-tech/agentic-toolkit --skill langgraph-dev-parallel-execution
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00067 $0.02698
Opus 5 $0.00034 $0.01349
Sonnet 5 $0.00013 $0.00540
Haiku 4.5 $0.00007 $0.00270

Measured yesterday against content hash 1d3309e142e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-execution-in-langgraph 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 yesterday.

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.

plugins/langgraph-dev/skills/langgraph-dev-parallel-execution/SKILL.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Execution in LangGraph

Parallel execution allows multiple nodes to process state concurrently, with results automatically merged using state reducers.

Fan-Out/Fan-In Pattern

from typing import Annotated, TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.types import Overwrite
import operator

class State(TypedDict):
    results: Annotated[list, operator.add]  # Accumulates results via concatenation
    input_data: str

def branch_1(state: State) -> dict:
    return {"results": [1, 2, 3]}

def branch_2(state: State) -> dict:
    return {"results": [4, 5, 6]}

def branch_3(state: State) -> dict:
    return {"results": [7, 8, 9]}

def combine_results(state: State) -> dict:
    """
    Process aggregated results from parallel branches.

    Note: Results are already combined by the state reducer (operator.add).
    This node performs post-processing (sorting) and uses Overwrite to
    replace the accumulated results rather than appending to them.
    """
    sorted_results = sorted(state["results"])
    return {"results": Overwrite(value=sorted_results)}

def fan_out(state: State) -> list[str]:
    """Route to multiple branches for parallel execution."""
    return ["branch_1", "branch_2", "branch_3"]

workflow = StateGraph(State)
workflow.add_node("branch_1", branch_1)
workflow.add_node("branch_2", branch_2)
workflow.add_node("branch_3", branch_3)
workflow.add_node("combine", combine_results)

# Fan-out from START to parallel branches (path_map ensures correct visualization)
workflow.add_conditional_edges(START, fan_out, ["branch_1", "branch_2", "branch_3"])

# Fan-in: all branches must complete before combine (list syntax)
workflow.add_edge(["branch_1", "branch_2", "branch_3"], "combine")
workflow.add_edge("combine", END)

# Compile the graph before invocation
graph = workflow.compile()

# Invoke the graph
result = graph.invoke({"input_data": "test", "results": []})

Result: result["results"] = [1, 2, 3, 4, 5, 6, 7, 8, 9] (sorted by combine_results after accumulation)

Read the full file on GitHub · 335 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. yesterday First seen · 335 lines · 67 tokens per session scan A 1d3309e142e0

Subscribe to this mod's changes

parallel-execution-in-langgraph is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,698 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens