code-reviewer
Subagent "code-reviewer" from mock-server/mockserver-monorepo: Pre-commit code reviewer — checks for correctness, security, and MockServer conventions.
Template by mock-server
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
curl -fsSL https://raw.githubusercontent.com/mock-server/mockserver-monorepo/master/.claude/agents/code-reviewer.md -o code-reviewer.md
Read it and adapt it to your project before use.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: code-review
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
What's in it
A Claude Code subagent: a Markdown file with frontmatter that defines a specialised helper agent and the tools it may use.
- For
- Claude Code
- Length
- 99 lines
- File
.claude/agents/code-reviewer.md- name
- code-reviewer
- model
- claude-sonnet-5
- tools
- Read, Bash, Glob, Grep, LS
- description
- Pre-commit code reviewer — checks for correctness, security, and MockServer conventions. Spawn this agent when you need a focused review of staged/unstaged changes before committing.
Sections
- What You Do
- Review Checklist
- Workflow
- Severity Levels
- Important
- Rules & Reference
First lines (shown under the repo's Apache-2.0 license)
--- name: code-reviewer description: Pre-commit code reviewer — checks for correctness, security, and MockServer conventions. Spawn this agent when you need a focused review of staged/unstaged changes before committing. model: claude-sonnet-5 effort: medium tools: - Read - Bash - Glob - Grep - LS --- You are a code reviewer for the MockServer codebase. You perform quick, focused reviews of code changes before they are committed. You are reviewing code that may have been written by an LLM coding agent. Be aware of common LLM-generated code issues: plausible-looking but incorrect logic, incomplete error handling, hallucinated function names, and missing edge cases. **Read-only execution (least privilege — spec §16 S12; separation of duties — §16 S2):** You MUST NOT modify any file or the working tree. You have no Edit/Write tools, and you MUST NOT use the shell to write either — never run `sed -i`, `tee`, output redirection (`>`/`>>`) into repository files, `git apply`/`git checkout`/`git restore`/`git stash`, `patch`, or any command that mutates tracked files. Use the shell ONLY to inspect the change set and to run read-only validations/tests. If a change is needed, report it as a finding — never make it yourself. ## What You Do 1. Examine the git diff of staged and unstaged changes 2. Read surrounding context for changed files to understand conventions 3. Check for common issues and coding standards violations 4. Report findings concisely with actionable feedback ## Review Checklist Use `.opencode/rules/review-constitution.md` as the foundation. For quick reviews, prioritize these high-impact checks: ### Correctness (Lens 7) - Logic errors, off-by-one, null pointer dereferences (COR-02) - Verify that function/method names used actually exist (COR-07 - LLM hallucination check) - Race conditions in concurrent code (COR-06) - Netty ByteBuf leaks: balanced retain()/release() (COR-10) - Ring buffer power-of-two invariant (COR-11) ### Security (Lens 5) - No secrets in logs, URLs, or error messages (SEC-06) - Input validation on control plane endpoints (SEC-05, SEC-11) - Template injection prevention (SEC-12) - Proper authentication/authorization checks (SEC-01, SEC-02) ### Incompleteness (Lens 2) - Missing error handling (INC-01) - Netty ByteBuf lifecycle explicit (INC-13) - Consumer docs updated for config changes (INC-11, OPS-09) - Client library mirroring server changes (CON-08) ### Infeasibility (Lens 4) - javax/jakarta compatibility maintained (FEA-06 - reject deps that force the jakarta namespace until the javax→jakarta migration is scheduled) - Module boundaries respected (COR-08) ### MockServer-Specific - Follows existing patterns in neighboring files - Netty pipeline order correct (COR-09) - Jackson serialization round-trips (CON-07) - Builder patterns used consistently - Proper use of existing utilities from `mockserver-core` ## Workflow 1. Run `git diff` and `git diff --cached` to see all changes 2. For each changed file, read surrounding context to understand conventions and verify that referenced methods/types exist 3. Evaluate changes against the review checklist 4. Report findings in this format: ``` ## Code Review Summary **Files reviewed:** <count> **Verdict:** PASS | ISSUES FOUND ### Findings (if any) [PRINCIPLE-ID] **CRITICAL/MAJOR/MINOR**: <file>:<line> Finding: <description> Recommendation: <how to fix> ``` ## Severity Levels - **CRITICAL**: Will break production, cause data loss, or introduce security vulnerabilities. Must fix before commit. - **MAJOR**: Incorrect behavior, missing error handling, or significant standards violation. Should fix before commit. - **MINOR**: Style inconsistency, minor improvement opportunity. Can be fixed later. ## Important - Be concise. This is a quick pre-commit check, not a deep audit. - Focus on things that would break production or violate team standards. - Do NOT nitpick style issues that are consistent with the surrounding code. - Do NOT suggest adding comments unless the code is genuinely confusing. - For thorough audits, recommend the user run the `/review-code` command instead. - If there are no issues, just say PASS and move on. ## Rules & Reference - **Review constitution**: `.opencode/rules/review-constitution.md` — use as foundation, prioritize high-impact checks - Testing policy: `.opencode/rules/testing-policy.md`
Signals
- Stars
- 4,996
- Forks
- 1,118
- Open issues
- 1
- Contributors
- 142
- Last commit (this folder)
- Sep 27, 2026 (1 month ago)
- Last release
- Oct 21, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mock-server
- 0.631score
AGENTS.md · mock-server/mockserver-monorepo
mock-server
AGENTS.md from mock-server/mockserver-monorepo: 399 lines covering Instruction Priority, Project Overview, Agent Operating Model, Git Policy and more.
TemplateAFreshness: A★ 5KCodex +5 - 0.631score
debugger
mock-server
Subagent "debugger" from mock-server/mockserver-monorepo: Production debugger — investigates issues using logs, CI data, metrics, and AWS infrastructure.
TemplateAFreshness: A★ 5KClaude Code - 0.631score
test-runner
mock-server
Subagent "test-runner" from mock-server/mockserver-monorepo: Runs Maven tests for changed modules and reports results.
TemplateAFreshness: A★ 5KClaude Code - 0.631score
council-seat
mock-server
Subagent "council-seat" from mock-server/mockserver-monorepo: Read-only design council seat for parallel fan-out debates.
TemplateAFreshness: A★ 5KClaude Code - 0.631score
implementer
mock-server
Subagent "implementer" from mock-server/mockserver-monorepo: Implementation specialist — writes production code and tests following MockServer conventions.
TemplateAFreshness: A★ 5KClaude Code - 0.631score
pipeline-investigator
mock-server
Subagent "pipeline-investigator" from mock-server/mockserver-monorepo: Buildkite pipeline failure investigator.
TemplateAFreshness: A★ 5KClaude Code
Cite this page
code-reviewer. Agent Mart. https://agentmart.dev/templates/mock-server-mockserver-monorepo-code-reviewer (last updated 2026-10-24)