langchain-agents-langgraph-code
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Node.js · Python
- Permissions
-
- Read-only
- Shell exec
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: langchain-agents-langgraph-code
description: Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't e…
category: ai
runtime: Node.js / Python
---
# langchain-agents-langgraph-code output preview
## PART A: Task fit
- Use case: Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't enough and you need explicit StateGraph control (multi-graph workflows, custom routing, non-standard state schemas, parallel branches). For the common case, use `create_agent` first (see middleware skill)..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “When to drop down to raw StateGraph / Things the docs won't warn you about / Production essentials (rules of thumb)” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't enough and you need explicit StateGraph control (multi-graph workflows, custom routing, non-standard state schemas, parallel branches). For the common case, use `create_agent` first (see middleware skill).”.
- **02** When the source has headings, the agent prioritizes “When to drop down to raw StateGraph / Things the docs won't warn you about / Production essentials (rules of thumb)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, run shell commands, write/modify files; may access external network resources; usually needs no extra API key.
## Running Rules
- read files, run shell commands, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, run shell commands, write/modify files.
Start with a small task and check whether the result follows “When to drop down to raw StateGraph / Things the docs won't warn you about / Production essentials (rules of thumb)”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: langchain-agents-langgraph-code
description: Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't e…
category: ai
source: tomevault-io/skills-registry
---
# langchain-agents-langgraph-code
## When to use
- Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't enough and you need exp…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “When to drop down to raw StateGraph / Things the docs won't warn you about / Production essentials (rules of thumb)” and keep inference separate from source facts.
- read files, run shell commands, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "langchain-agents-langgraph-code" {
input -> user goal + target files + boundaries + acceptance criteria
context -> When to drop down to raw StateGraph / Things the docs won't warn you about / Production essentials (rules of thumb)
rules -> SKILL.md triggers / order / output contract
runtime -> Node.js / Python | read files, run shell commands, write/modify files | may access external network resources
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}LangGraph: editorial guidance
For API reference (signatures, imports, exhaustive method lists), use the mcpdoc MCP tools: fetch_docs("https://docs.langchain.com/oss/python/langgraph/..."). This skill is the opinions layer; the docs are the facts layer.
When to drop down to raw StateGraph
Most agents do NOT need this. Use create_agent(...) + middleware first (see the langchain-agents-middleware skill). Drop down to StateGraph only when:
- Multiple LLM calls in a single graph with custom routing between them.
- Branches that run in parallel and merge.
- Non-message state (custom dataclasses, dicts, dataframes flowing through nodes).
- Multi-graph workflows where one graph calls another as a subgraph.
If your problem fits "one model, some tools, in a loop" — even if the loop is complex — create_agent is the right tool. Don't reach for StateGraph out of habit.
Things the docs won't warn you about
- A node returning
{}is a no-op; returnNoneto signal "no state change" cleanly. add_conditional_edgesmappings must includeENDif any branch terminates — leaving it out is a silent bug, not an error.compile()is not idempotent acrossbind_tools— rebind tools, then re-compile.langgraph devreloads on file change; if it stops reloading, the graph likely failed to import — check the terminal for the exception.- A graph with
interrupt()calls but no checkpointer will throw at invoke time, not at compile time. Always pairinterrupt()withcompile(checkpointer=...).
Production essentials (rules of thumb)
- Always pass a
thread_idinconfig={"configurable": {"thread_id": ...}}for any agent with persistent state. A missingthread_idsilently starts a fresh thread. InMemorySaveris for dev only. Production =PostgresSaver(multi-instance safe) orSqliteSaver(single-node, low-volume). State dies with the process forInMemorySaver.- Resume an interrupted thread by passing
Noneas input with the samethread_id. The runtime picks up where the interrupt fired. - Custom state schemas need reducers.
Annotated[list, add_messages]appends; without the reducer, each node replaces the field instead of accumulating. - For node-level retries on raw
StateGraph, useRetryPolicy. Forcreate_agentagents, preferToolRetryMiddleware/ModelRetryMiddleware— same effect, cleaner composition.
Doc URLs to fetch with mcpdoc
https://docs.langchain.com/oss/python/langgraph/graph-api.md—StateGraph, nodes, edgeshttps://docs.langchain.com/oss/python/langgraph/durable-execution.md— checkpointers +thread_idhttps://docs.langchain.com/oss/python/langgraph/streaming.md—stream_modemodeshttps://docs.langchain.com/oss/python/langgraph/persistence.md— Postgres / Sqlite checkpointershttps://docs.langchain.com/oss/python/langgraph/subgraphs.md— multi-graph composition
When the user is mid-task and you need a method signature or import path, fetch from these URLs. Don't guess.
Source: cwijayasundara/agent_cli_langchain — distributed by TomeVault.
Decide Fit First
create_agent(...)+ middleware isn't enough and you need explicit Stat…Design Intent
How To Use It
Boundaries And Review