existential-birds avatar

Langgraph Code Review

This is a sequenced code reviewer that catches LangGraph footguns before they bite you in production. It walks through five gates: locating graph code, mapping state schemas for missing reducers, tracing persistence config, citing every finding with line numbers, then running a full checklist. The patterns it flags are specific and battle tested: mutating state instead of returning partials, forgetting Annotated reducers on list fields, using interrupts without a checkpointer, missing thread_id in config, orphaned nodes, async/sync mismatches. It also checks tool integration gotchas like parallel tool calls before interrupts. Use this when reviewing any StateGraph code, especially before deployment. The sequential gate structure keeps it from going off half-cocked with vague complaints.

skills.sh installs
887
GitHub stars
87
last updated
Aug 21, 2026

Install

$ npx -y skills add existential-birds/beagle --skill langgraph-code-review --agent claude-code

Installs into .claude/skills of the current project.

Files

LangGraph Code Review

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

Anti-confabulation (gate 0 — runs before every other gate)

Before issuing any finding — flag a bug, anti-pattern, or improvement — you MUST echo the exact artifact you are judging, quoted from a source you read in this turn:

  • The code finding: its file:line plus the cited code, read freshly now.
  • The graph/state code under review: the StateGraph, node, edge, or state-schema snippet your finding depends on, quoted from the file you just read.

The artifact is the only source of truth. Never infer what you are reviewing from the branch name, the working directory, surrounding files, or recollection. If your mental model differs from the freshly read source, the source wins. A finding issued without a same-turn echo of its target is invalid — emit the echo first, or do not emit the finding.

This gate exists because an LLM under contextual priming will confidently flag code that is not in the file. It runs before the gates below.

Review gates (sequenced)

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

Sponsors

Details

Repository
github.com/existential-birds/beagle
Categories
Git & Pull Requests, Code Review & Quality, AI & Agent Building

More from existential-birds/beagle

All 40
1bitjaru avatarss-reviewbitjaru/styleseedReview UI code for design system compliance, accessibility, and best practices864skills.sh installs
2encoredev avatarencore-code-reviewencoredev/skillsReview existing Encore.ts code for best practices and common anti-patterns.862skills.sh installs
3huangwb8 avatarsystematic-literature-reviewhuangwb8/chineseresearchlatex当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词,多源检索→去重→AI 逐篇阅读并评分(1–10分语义相关性与子主题分组)→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作(固定摘要/引言/子主题/讨论/展望/结论),保留正文字数与参考文献826skills.sh installs
4affaan-m avatarprediction-market-risk-reviewaffaan-m/everything-claude-codeprediction market risk review801skills.sh installs
5majiayu000 avatargithub-trendingmajiayu000/claude-arsenalgithub trending788skills.sh installs
6bobmatnyc avatargithub-actionsbobmatnyc/claude-mpm-skillsGitHub Actions CI/CD workflows for automating build, test, and deployment771skills.sh installs