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
- Brainstorming — Transform rough ideas into fully-formed designs through structured questioning and alternative exploration 27.9k ★
- 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
Draftingboard
A visual legal matter canvas — artifacts orbit a contract and run as agentic workflow steps behind human appro
Facode
FA Code is a Claude Code–style CLI coding agent with [REA (Reverse Engineering Anything)].it's an autonomous t
Opencode Vibe
🏄♂️ Next.js 16 web UI for OpenCode - real-time chat with streaming, SSE sync, and React Server Components
Airdrop Assessment
Walks a Solana airdrop mechanism through four staged checks — the essential-managerial-efforts (Howey prong) a
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