PR Review Agent — Design skill for Claude Code
LangGraph.js PR-review agent on Claude: per-file analysis via MCP, coverage and risk checks, structured review, human approval before posting, checkpointed and resumable, with a Next.js UI streaming s.
How to install PR Review Agent
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open pshashanka/pr-review-agent and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What PR Review Agent does
LangGraph.js PR-review agent on Claude: per-file analysis via MCP, coverage and risk checks, structured review, human approval before posting, checkpointed and resumable, with a Next.js UI streaming steps over SSE.
Alternatives in Design
- Kode Agent — Kode Agent — Design for post-human workflows 5k ★
- Site — Crawl a whole site and synthesize ONE canonical design system across all pages — unified tokens, coverage map 3.6k ★
- Clui Cc — A lightweight, transparent desktop overlay for Claude Code on macOS 956 ★
README
pr-review-agent
A LangGraph.js agent that reviews a pull request: it summarizes the change, analyzes each file, checks whether the tests cover it, flags risks, and writes a structured review. **Nothing is posted until a human approves it.** It comes with a CLI and a Next.js UI that streams the agent's steps live.
It's part two of a three-part series on production AI engineering for code review:
| Repo | Role |
|---|---|
| `mcp-repo-tools` | MCP server: the agent's only, read-only view of the repository |
| pr-review-agent (this) | The agent: orchestration, model calls, human approval, publishing |
gameable-tests-bench |
Next: tasks with deliberately weak tests, and a grader that catches agents gaming them |
How it works
flowchart TD
start([base, head, PR?]) --> load[loadChange
list_changed_files → pinned SHAs]
load --> plan[planReview
skip lockfiles/generated/binary/hidden · fetch patches]
plan --> summarize[summarizeDiff]
plan -->|Send × N files| analyze[analyzeFile
bounded read_file / search_code loop]
plan --> coverage[checkCoverage
name pairing + optional run_tests + model]
plan --> risks[flagRisks
rules + model]
summarize & analyze & coverage & risks --> synth[synthesize
verdict + curated finding ids]
synth --> validate[validateReview
real ids only · no approve with a blocker/major]
validate --> approval{{humanApproval
interrupt}}
approval -->|approve / edit| post[postReview
GitHub or file · idempotent]
approval -->|rejec
Related Skills
Next Feature
Pick the next unblocked feature from the backlog and write its technical design for human approval.
Sampled
Don't bite someone else's style. A Claude Skill that checks whether the idea you're about to publish already b
Opencode Vibe
🏄♂️ Next.js 16 web UI for OpenCode - real-time chat with streaming, SSE sync, and React Server Components
Writing Style Extractor
Claude Code skill: Extract writing style DNA from any content. Produces structured JSON profile + markdown rep
MCP Tasks Next Large
Execute large tasks with detailed analysis, design, and user interaction
MCP Tasks Next Medium
Execute medium complexity tasks with analysis, design, and user interaction
Related Agents
Pipeline Optimizer
Reviews the LLM/agent pipeline — model selection, LangGraph wiring, MCP client lifecycle, async/streaming beha
LLM Workflow Engineer
Use when building LangGraph workflows, agents, RAG systems, structured-output nodes, streaming chat surfaces,
Approval Gate
HumanLayer-inspired approval gate. Enforces human-in-the-loop for HIGH-stakes operations. Classifies actions b