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
  • Keep rule files in sync
  • Sync rules across repos
  • Why Codex ignores it
  • 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
  • Make Claude Code remember
  • Claude Code auto memory
  • GitHub Copilot Memory
  • Claude Tag vs Claude Code
  • Codex memories
  • Cursor memories
  • Memory or documentation?

Team knowledge and shared conventions

  • Claude Code team memory
  • Stop correcting agents
  • 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
  • Review PRs against team rules
  • 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

How to stop correcting AI coding agents on the same conventions

Published November 22, 2026

You tell Claude Code to write a migration, not reset the database. Next session, a teammate's agent does the reset. You correct it again.

Why the usual fix falls short

Every agent has an instruction file: CLAUDE.md, AGENTS.md, Cursor rules, copilot-instructions.md. They help. They also have limits:

  • Someone has to write and update them.
  • They go stale as the code moves (stale rules).
  • They are per repo, and per agent (keeping them in sync).
  • A long file is loaded whole, so important rules get lost (why a growing CLAUDE.md stops working).

Linters like ESLint and Prettier handle mechanical rules well. Keep using them. Conventions that need judgment still land on you.

What Harbor does

  • It learns the rule. When someone says it once, in a coding session, a review thread, Slack or a doc, Harbor keeps it as a rule. You choose whether every rule waits for a person to approve it.
  • It hands over only what fits. Before each prompt, the agent gets at most three ranked rules matched to the task and the files it touches.
  • It reaches everyone. Every teammate gets the same rules, in Claude Code, Codex, Cursor and GitHub Copilot, on any machine and repo the Space covers.
  • It checks the result. Each pull request is reviewed against your rules (how to review pull requests against your own team's rules).
  • It keeps rules true. Conflicts, disputes and stale rules are handled.

A controlled test

In a controlled test with one saved rule, the agent got 10 of 10 right on the first try, with 0 corrections typed and 38% less agent time. This is a test, not a customer result. The setup and what it leaves out are on the Harbor home page.

Start

Run npx harborloop init.

Connects Claude Code, Codex, Cursor and GitHub Copilot. Free for you and one teammate. No card. No end date.

Related: how to stop Claude Code and Cursor from making the same mistakes on your codebase, and how to make Claude Code remember your corrections.

Questions

How do I stop correcting AI coding agents on the same team conventions every session?

Write the convention into the file each agent reads, such as CLAUDE.md, AGENTS.md, Cursor rules or copilot-instructions.md, and keep linters for mechanical rules. Files need someone to write and update them, go stale, and are per repo and per agent. Harbor learns the convention when someone says it once and gives every teammate's agent the rules that fit each task.

Why do CLAUDE.md and AGENTS.md not stop the repeated corrections on their own?

Someone has to write and update them, they go stale as the code moves, they are per repo and per agent, and a long file is loaded whole, so important rules get lost.

How many rules does Harbor give an agent?

At most three ranked rules before each prompt, matched to the task and the files it touches, not the whole rulebook.

Which coding agents does Harbor work with?

Claude Code, Codex, Cursor and GitHub Copilot, connected with npx harborloop init. It is free for you and one teammate, with no card and no end date.

More on Team knowledge and shared conventions

  • Claude Code team memory: what is shared, what is not
  • How to stop Claude Code and Cursor from making the same mistakes on your codebase
  • Who should own CLAUDE.md and AGENTS.md on a team?
  • Obsidian as a second brain for Claude Code, and where it stops

How Harbor keeps a team’s knowledge →

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