langgraph-code-review

Installation
Summary

Catches common bugs in LangGraph state management, graph structure, and async patterns.

  • Identifies 20+ critical issues including state mutations, missing reducers, invalid conditional edge returns, and checkpointer configuration errors
  • Covers state schema problems like improper use of add_messages, full-state returns, and Pydantic models without annotations
  • Detects graph structure issues: missing entry points, unreachable nodes, incomplete conditional paths, and undeclared Command destinations
  • Flags async anti-patterns, tool integration mistakes (unpaired tool calls, parallel interrupts), and production checkpointing errors
  • Includes a 10-item code review checklist for validating LangGraph implementations
SKILL.md

LangGraph Code Review

When reviewing LangGraph code, check for these categories of issues.

Review gates (sequenced)

Complete in order. Each step has an objective pass condition before moving on.

  1. Locate graph code — Search the review scope for StateGraph, compile(, invoke, ainvoke, add_node, add_edge, add_conditional_edges. Pass: a short list of file paths (or explicit “none in scope” after searching).

  2. Map state schema — For each graph state type (TypedDict, BaseModel, etc.), list fields that hold lists, dicts, or messages and whether Annotated + reducers (add_messages, operator.add, …) are present. Pass: every such field is either covered by a reducer pattern below or explicitly flagged as intentional overwrite.

  3. Trace persistence — If interrupts, thread_id, or checkpoint APIs appear, follow them to compile(..., checkpointer=...) and invocation config. Pass: behavior matches the interrupt/checkpointer/thread_id guidance below—or you document a concrete mismatch with file:line.

  4. Report with evidence — For each finding you will deliver, record file path and line number(s) (or a minimal quoted snippet). Pass: no critical or high-severity issue is stated without that citation.

  5. Run the checklist — Use the checklist at the end of this skill; each item is satisfied, not applicable (with reason), or open with evidence. Pass: no item left silently unchecked.

Critical Issues

Related skills

More from existential-birds/beagle

Installs
827
GitHub Stars
57
First Seen
Jan 20, 2026