Blog
Notes on team context for AI coding agents
What Claude Code, Cursor, Codex and Copilot actually read. Why a growing CLAUDE.md stops working, and what the research found. How a team's decisions reach every agent, and how to tell which rules get used.
Does Claude Code read AGENTS.md?
Yes, since v2.1.277, but by default only when the project has no CLAUDE.md. The four modes, where to set them, and why some sessions still skip it.
Claude Code skills: how to write SKILL.md and when to use one
A Claude Code skill is a folder with a SKILL.md that loads only when a task needs it. How to write one, the frontmatter fields, and why skills do not trigger.
Claude Code hooks: a practical guide with examples
Claude Code hooks run commands at fixed points in a session and, unlike CLAUDE.md, always run. The key events, config, and how to block a command with exit 2.
What is claude-mem, and is it enough for a team?
claude-mem gives Claude Code memory across sessions. How it works, how to install it, and what personal memory does not cover for a team.
Claude Code best practices, and what changes for a team
Claude Code best practices start from one constraint: context fills fast. Anthropic’s list, condensed, plus the practices a team needs once rules are shared.
The Karpathy CLAUDE.md: what is in it and does it help?
The Karpathy CLAUDE.md is 65 lines of four coding principles, written by a developer from Karpathy’s January 2026 post. What it says, what it cannot do.
AGENTS.md vs CLAUDE.md: which tools read which
AGENTS.md is the shared file Codex, Cursor and Copilot read; CLAUDE.md is Claude Code's. Which tool reads which, symlink vs @import, and one source of truth.
Cursor rules best practices, and why rules stop working
Cursor rules live in .cursor/rules as .mdc files. Which mode to use, how to share them with a team, and a checklist for rules that do not fire.
How to write copilot-instructions.md for GitHub Copilot
copilot-instructions.md gives GitHub Copilot repo-wide instructions. How to write it, path-specific .instructions.md files, and which surfaces read AGENTS.md.
Why does Claude ignore my CLAUDE.md?
CLAUDE.md is context, not enforcement. Rules lose when they never loaded, conflict, go stale, drown in irrelevant ones, or sit deep in a long session.
How long should CLAUDE.md be?
Anthropic says under 200 lines. The file is in context for the whole session, so cut what the agent can read from the code and keep commands and gotchas.
Should you commit CLAUDE.md and the .claude folder?
Commit CLAUDE.md, settings.json, rules, skills, agents and .mcp.json. Keep CLAUDE.local.md and settings.local.json out of git. What git still does not solve.
Claude Code memory vs Codex, Cursor and Copilot memory
Claude Code and Codex keep memory on your machine, Copilot Memory per repository, and Cursor dropped Memories for rules. None holds your team's decisions.
CLAUDE.md vs skills vs hooks vs rules vs subagents
Where each team rule belongs in Claude Code: CLAUDE.md for every session, path rules for one area, skills on demand, hooks for must-never. Plus Cursor.
Why does my AI agent keep making the same mistake?
Your correction lived in one chat, and the next session starts fresh. Write corrections down as rules with reasons; use a hook for what must never run.
How to turn PR review comments into agent rules
Keep review comments the author accepted and that recur, rewrite each as a short rule with its reason and PR, and put it where every coding agent loads it.
How to get Slack decisions into AI coding agents
Coding agents never see Slack decisions unless someone pastes them or the agent searches. Capture them once, approve them, and serve them to every agent.
What is a company brain?
A company brain captures what a team decided where it decides, gets it approved, keeps it current, and serves the relevant facts to people and AI agents.
Context engineering for Claude 5: what changes for teams
Anthropic cut 80% of Claude Code's system prompt with no eval loss. For teams: a short CLAUDE.md of gotchas, judgment over rules, skills, and a gap in memory.
Context rot and stale rules in CLAUDE.md
Context rot is accuracy falling as input grows. Stale rules, like renamed paths and reversed decisions, are worse: relevant, wrong, and sent every turn.
Is AGENTS.md useful? What the research found
Hand-written AGENTS.md files help a little, generated ones hurt a little, both cost about 20% more. What ETH, McMillan, Vercel and rule studies found.
Architecture decision records (ADRs) for AI coding agents
Agents follow an ADR only if it is in context when they write the code. Keep ADRs short in the repo, index them in AGENTS.md, and mark superseded ones.
What is AI agent memory poisoning?
Untrusted content written into an agent's persistent memory that steers later sessions. OWASP lists it as ASI06. Stale memory is the daily form.
MCP memory servers for teams
MCP memory servers like mem0, Basic Memory and Graphiti give agents recall. A team also needs review before serving, contradiction handling and expiry.
Share memory between Claude Code, Cursor and Codex
Claude Code, Cursor and Codex each forget what the others were told. Harbor is one company brain: a CLI on the machine and an MCP server in the chat.
Why a growing CLAUDE.md stops working
A CLAUDE.md is in the prompt on every call. ETH Zurich found a developer-written context file moved success 2.4 points, not significant, and cost 20 percent more.
Served vs cited: measuring which rules your agents use
Retrieval tools count what they sent. They do not count what the answer used. Served vs cited is that split. A citation is not a proof of obedience.