Langgraph

What it does

When your agent uses it

• Building LangGraph pipelines
• Multi-agent systems

Example prompts

• “/langgraph”

Requirements

• Python 3
• Compatibility (from SKILL.md): Claude Code 2.1.277+.
• Pre-approved tools (allowed-tools): Read, Glob, Grep, WebFetch, WebSearch

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

1. 1Forgetting add reducer (overwrites instead of accumulates)
2. 2Mutating state in place (breaks checkpointing)
3. 3No END fallback in routing (workflow hangs)
4. 4Infinite retry loops (no max counter)
5. 5Side effects in router functions
6. 6Too many tools per agent (context overflow)
7. 7Raising exceptions in tools (crashes agent loop)
8. 8No checkpointer in production (lose progress on crash)
9. 9Wrapping interrupt() in try/except (breaks the mechanism)
10. 10Not transforming state at subgraph boundaries
11. 11Forgetting .result() on Functional API tasks
12. 12Using set_entry_point() (deprecated, use add_edge(START, ...))

What it can do on your machine

Read from SKILL.md and the folder at commit 0ef71d2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • WebFetch
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Claude Code 2.1.277+.

  From compatibility in the SKILL.md frontmatter.

Context cost

Langgraph loads about 4.2k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 1,300 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~94

When it runs · the whole SKILL.md, loaded when a task matches

~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yonatangross/orchestkit at commit 0ef71d2, republished under its MIT licence (© yonatangross). 1,300 words, ~4,204 tokens.

name

langgraph

description

LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.

allowed-tools

Read, Glob, Grep, WebFetch, WebSearch

compatibility

Claude Code 2.1.277+.

license

MIT

user-invocable

false

disable-model-invocation

true

effort

high

upstream-version-tested

1.2.12

metadata.owner-agent

workflow-architect

metadata.category

document-asset-creation

metadata.version

2.3.0

metadata.author

OrchestKit

metadata.complexity

high

from langgraph.types import RetryPolicy, TimeoutPolicy
from langgraph.errors import NodeError

builder.add_node(
    "call_vendor",
    call_vendor,
    timeout=TimeoutPolicy(run_timeout=300, idle_timeout=30),
    retry_policy=RetryPolicy(max_attempts=3),
    error_handler=lambda state, error: Command(
        update={"failure": f"{error.node}: {error.error}"}, goto="degraded_path"
    ),
)

from langgraph.graph import StateGraph
from langgraph.types import CachePolicy
from langgraph.cache.sqlite import SqliteCache

graph = StateGraph(State)
graph.add_node(
    "expensive_fetch",
    fetch_fn,
    cache_policy=CachePolicy(ttl=3600, key_func=lambda s: s["query"]),
)
# RedisCache(url=...) for distributed workers
compiled = graph.compile(cache=SqliteCache("cache.db"))

# defer=True — node execution is deferred until the run is about to end,
# i.e. after every other upstream node has completed
graph.add_node("aggregate", aggregate_fn, defer=True)

# Model middleware — no subclassing required.
# create_react_agent is @deprecated since v1.0; use create_agent from langchain.agents.
# The legacy pre_model_hook/post_model_hook are now before_model/after_model middleware.
from langchain.agents import create_agent

agent = create_agent(
    model=model,
    tools=tools,
    middleware=[compress_history, redact_pii],  # before_model / after_model hooks
    system_prompt="...",                          # prompt= renamed to system_prompt
)

from langgraph.graph import StateGraph, START, END
from langgraph.types import Command
from typing import TypedDict, Annotated, Literal
from operator import add

class State(TypedDict):
    input: str
    results: Annotated[list[str], add]

def supervisor(state) -> Command[Literal["worker", END]]:
    if not state.get("results"):
        return Command(update={"input": state["input"]}, goto="worker")
    return Command(goto=END)

def worker(state) -> dict:
    return {"results": [f"Processed: {state['input']}"]}

graph = StateGraph(State)
graph.add_node("supervisor", supervisor)
graph.add_node("worker", worker)
graph.add_edge(START, "supervisor")
graph.add_edge("worker", "supervisor")
app = graph.compile()

© yonatangross, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 45 other files in src/skills/langgraph of yonatangross/orchestkit.

• SKILL.md
• metadata.json
• rules/_sections.md
• rules/_template.md
• rules/checkpoints-recovery.md
• rules/checkpoints-setup.md
• rules/checkpoints-store.md
• rules/functional-entrypoint.md
• rules/functional-migration.md
• rules/functional-task.md
• rules/human-in-loop-approval.md
• rules/human-in-loop-feedback.md
• rules/human-in-loop-interrupt.md
• rules/parallel-error-isolation.md
• rules/parallel-fanout-fanin.md
• rules/parallel-map-reduce.md
• rules/platform-deployment.md
• rules/platform-double-texting.md
• rules/platform-remote-graph.md
• rules/resilience-error-handlers.md
• … and 26 more

Open the folder on GitHubat commit 0ef71d2