Skip to content
How it learnsFrom coding sessions, reviews, Slack and docs.Only what fitsEach session gets the few rules its task needs.Pull request reviewEvery PR checked against your team’s rules.Keep it trueA gate, conflicts, disputes and stale rules, handled.HandoffsCarry the work to another session or a teammate.SecurityWhat it sends, what it changes and how to leave.
Engineering teamsOne agent or several: what one person learns, every session uses.PR review onlyInstall the GitHub App. Nothing on anyone’s machine.Teams that mix agentsClaude Code, Cursor, Codex and Copilot, the same rules.On your ownYour corrections follow you across repos, machines and agents.Book a call30 minutes with Roei, if you want a hand. Never required.
DocsPricingSign in
Connect your agents →
For teamsOn your ownPR review onlyHow it learnsOnly what fitsPull request reviewKeep it trueSecurityDocsPricingSign inConnect your agents →
Home/Blog

Blog

AGENTS.md, Cursor rules and Copilot instructions

  • AGENTS.md vs CLAUDE.md
  • Sync rules across repos
  • Why Codex ignores it
  • Keep rule files in sync
  • 3,905 files checked
  • Why Copilot ignores it
  • Cursor Team Rules
  • Cursor rules
  • copilot-instructions.md
  • Claude Code and AGENTS.md
  • AGENTS.md research

CLAUDE.md and context engineering

  • Why Claude ignores it
  • Test a CLAUDE.md rule
  • One CLAUDE.md for all projects
  • Context engineering, Claude 5
  • CLAUDE.md length
  • Which rules got used
  • Context rot, stale rules
  • Growing CLAUDE.md
  • Claude Code best practices
  • Karpathy CLAUDE.md
  • Committing CLAUDE.md

Built-in agent memory

  • Agent memory compared
  • Claude Code auto memory
  • GitHub Copilot Memory
  • Make Claude Code remember
  • Claude Tag vs Claude Code
  • Codex memories
  • Cursor memories
  • Memory or documentation?

Team knowledge and shared conventions

  • Claude Code team memory
  • Stop repeated mistakes
  • Who owns CLAUDE.md
  • Claude Code second brain
  • Shared memory across agents
  • Hand off between agents
  • Company brain
  • Slack decisions
  • Memory poisoning
  • Karpathy's LLM wiki
  • ADRs for agents

Skills, hooks and permissions

  • Rules vs skills
  • Block banned commands
  • Claude Code hooks
  • Codex skills
  • Auto mode
  • CLAUDE.md vs skills vs hooks
  • Claude Code skills

AI code review and PR guardrails

  • PR review against AGENTS.md
  • PR review for team conventions
  • Review comments to rules

Memory tools and alternatives

  • Best company brain tools
  • Unblocked alternatives
  • claude-mem alternatives
  • Supermemory alternatives
  • Mem0 alternatives
  • claude-mem
  • Best MCP memory servers
  • Supermemory Company Brain alternatives

Blog

Best tool to review pull requests against your team's coding conventions

Published November 21, 2026

The right answer depends on what kind of convention you mean.

Hard, mechanical rules

Formatting, banned imports, naming. Use a linter or a rule engine: ESLint, Ruff, Checkstyle, Semgrep. They are deterministic, and you can run them as required CI checks. No AI reviewer beats that for these rules.

Conventions an AI reviewer can read

ToolWhere its rules liveGood fit
CodeRabbit.coderabbit.yaml and path instructionsPer-path conventions, fast setup
GreptileCustom rules plus a whole-repo indexRules about existing helpers and cross-service calls
GitHub Copilot code reviewRepo instruction filesTeams already on Copilot who want minimal setup
HarborThe rules your team already uses, including CLAUDE.md, AGENTS.md and .claude/rulesTeams that run several coding agents and want the same rules in the session and on the PR

Which rule files each reviewer reads, and from which branch, is in which AI code reviewers read AGENTS.md and CLAUDE.md.

What Harbor does differently

Harbor reviews each pull request for bugs and for your team's rules. It reads your CLAUDE.md, AGENTS.md and .claude/rules whole, from the base branch. A PR cannot rewrite the rules it is judged by.

The rules are not only a file someone maintains. Harbor learns them from coding sessions, review threads, Slack and docs. You can set a gate so each rule waits for a person to approve it.

The same rules also go to the agent before the code is written. Before each prompt, the agent gets the few rules that fit the task. So the review catches what slipped through, and fewer things slip through.

You can start with review only. Install the GitHub App and turn on Code review. Nothing runs on anyone's machine.

Caveats

  • AI reviewers are probabilistic. Keep linters for hard requirements.
  • If your team uses one agent and one Git host and rules rarely change, a built-in option may be enough.
  • Harbor's value grows when several agents are in play.

Try it

Harbor is free for you and one teammate, no card, and Free includes 10 reviews. Install the GitHub App to start with PR review.

Questions

What is the best tool to review pull requests against my team's coding conventions?

For formatting, banned imports and naming, a linter or rule engine such as ESLint, Ruff, Checkstyle or Semgrep, run as a required CI check. For conventions a person has to read, an AI reviewer: CodeRabbit, Greptile, GitHub Copilot code review or Harbor. Harbor fits teams that run several coding agents and want the same rules in the session and on the pull request.

Can a pull request change the rules it is reviewed against?

With Harbor, no. It reads CLAUDE.md, AGENTS.md and .claude/rules whole, from the base branch, so a pull request cannot rewrite the rules it is judged by.

Do I still need a linter if I use an AI code reviewer?

Yes. AI reviewers are probabilistic. Keep linters and CI checks for hard requirements, and use the AI reviewer for conventions a machine cannot verify.

More on AI code review and PR guardrails

  • Which AI code reviewers read AGENTS.md and CLAUDE.md?
  • How to turn PR review comments into agent rules

Review pull requests against your team’s rules →

Your team’s rules, in every agent, checked on every PR.

Harbor is shared memory for your team’s Claude Code, Cursor, Codex and Copilot. Free for you and one teammate. No card. No end date.

Start free →

Product

  • How it learns
  • Only what fits
  • Pull request review
  • Keep it true
  • Handoffs
  • The result
  • Security
  • For coding agents
  • Pricing

Developers

  • Docs
  • Quickstart
  • Install
  • CLI
  • MCP server
  • Served and cited
  • Rule-file checker
  • Blog

Guides

  • Why Claude ignores CLAUDE.md
  • AGENTS.md vs CLAUDE.md
  • Share Claude Code memory with a team
  • Why Codex ignores AGENTS.md
  • Why Cursor ignores rules
  • Copilot instructions vs AGENTS.md
  • Shared memory across agents
  • Copilot Memory and Dreaming

Compare

  • All comparisons
  • vs Mem0
  • vs Zep
  • vs Unblocked
  • vs ByteRover
  • vs Cognee
  • vs Hindsight
  • vs OpenViking
  • vs Supermemory
  • vs Glen
  • vs MemPalace
  • vs Sentra
  • vs Trail-code

Company

  • Questions
  • Contact
  • X
  • LinkedIn
  • Privacy Policy
  • Terms of Service
  • Data Processing Agreement
  • Refund Policy
© 2026 HarborConnect your agents