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.
Supermemory alternatives for coding agents (2026)
Harbor, Cognee, Mem0, Zep, Letta, ByteRover, claude-mem and a plain CLAUDE.md, checked against their own docs, for a team's Claude Code, Codex and Cursor.
Which AI code reviewers read AGENTS.md and CLAUDE.md?
CodeRabbit, Copilot code review, Claude Code Review, Bugbot and Harbor: which rules file each reads in a pull request, and which branch it reads it from.
A second brain for Claude Code, and where it stops
A Claude Code second brain is a markdown vault with a CLAUDE.md at the root. What Claude loads from it, how to set one up, and why it stays yours alone.
Why does Copilot ignore copilot-instructions.md?
Inline suggestions never read it, each Copilot surface reads different files, settings switch them off, and applyTo globs miss. How to check what loaded.
Cursor Team Rules: how to share Cursor rules with a team
Cursor Team Rules on Team and Enterprise plans: how they work, when they override Project Rules, and how Copilot and Claude Code org rules differ.
Rules vs skills: Cursor, Claude Code, Copilot and Codex
A rule loads every session or by file path; a skill loads when its description fits the task. How Cursor, Claude Code, Copilot and Codex split the two.
Claude Tag vs Claude Code: what Claude in Slack remembers
Claude Tag keeps memory per Slack channel and workspace. What it remembers, what loads from your repo, pricing, Teams, and why none of it reaches Claude Code.
GitHub Copilot Memory and Dreaming: where memories live
Copilot Memory keeps repository facts on GitHub for 90 days, and Dreaming tends them in the background. Where they live, who sees them, how to turn it off.
Codex memories: turn them on, find them, share them
Codex memories are off by default and stay in ~/.codex on one machine. How to turn them on, what the files hold, and whether ChatGPT or Claude Code see them.
Does Cursor have memory? What happened to Cursor Memories
Cursor removed Memories in 2.1. What it keeps instead in 2026: rules, AGENTS.md, Automations memories and Projects shared context, and what other agents read.
Claude Code auto memory: where MEMORY.md lives and how to turn it off
Claude Code auto memory is on by default. Where MEMORY.md lives, how much of it loads, why it seems not to work, and how to see, clear or turn it off.
Claude Code team memory: what is shared, what is not
Claude Code has no team memory you can turn on. What your team already shares, what stays on one machine, and how teams close the gap.
Supermemory Company Brain alternatives (2026)
Supermemory shut its hosted Company Brain on 9 September 2026. Self-host the open-source build, or move to Unblocked, Cognee or Harbor. What each one keeps.
We checked 3,905 CLAUDE.md and AGENTS.md files on GitHub
In 1 in 6 repos that keep both files, Claude Code never loads the AGENTS.md. What 3,905 public CLAUDE.md and AGENTS.md files show, and how we sampled them.
Why does Codex ignore my AGENTS.md?
Codex reads AGENTS.md from the repo root down to your folder, cuts it at 32 KiB without a warning, and skips untrusted projects. How to check what loaded.
Mem0 alternatives for coding agents (2026)
Cognee, Supermemory, Zep, Basic Memory, claude-mem and Harbor, checked against their own docs, by the reason you're leaving Mem0's coding plugin.
Codex skills: SKILL.md, the .agents/skills folder, and $name
How Codex skills work: the SKILL.md format, where Codex looks (.agents/skills), running one with $name, allow_implicit_invocation, and sharing skills with Claude Code.
Karpathy's LLM wiki: how it works, and what a team needs to add
Andrej Karpathy's LLM wiki, read from his gist: the three layers, ingest, query and lint, the tools built on it, and what breaks when a team shares one.
Claude Code auto mode vs --dangerously-skip-permissions
Auto mode runs Claude Code tool calls without asking after a classifier check. --dangerously-skip-permissions skips the classifier. Deny rules block in both.
Do coding agents need memory or documentation?
Neither, as usually built. Five 2026 papers on agent memory, shared memory and agent docs, and what a team should give its coding agents instead.
The best company brain tools for coding agents (2026)
Harbor, Unblocked, Packmind, Cognee, ByteRover and Mem0, checked against their own pages: where the rules come from, who decides, and what each costs.
Does Claude Code read AGENTS.md?
Yes, since v2.1.277, and in every session since v2.1.281. By default only without a CLAUDE.md: the four modes, and the two traps that switch it off.
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 needed. How to write one, which agents read it, how to test it, and why it won't fire.
Claude Code hooks: a practical guide with examples
Claude Code hooks run at fixed points and always run. Examples: block a command, format on edit, run tests before Claude stops, plus Codex and Cursor hooks.
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 for teams
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 file Codex, Cursor, Copilot and Antigravity read; CLAUDE.md is Claude Code's. Who reads which in October 2026, and one source of truth.
Cursor rules best practices, and why Cursor ignores them
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.
copilot-instructions.md vs AGENTS.md: how to write it for 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? Under 200 lines (median 81)
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.
How to make Claude Code remember your corrections
Claude Code starts each session fresh, so a correction made in chat is lost. To make it remember across sessions, write a rule with its reason, or a hook.
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.
The best MCP memory servers for Claude Code and teams (2026)
Harbor, Supermemory, Basic Memory, Zep, Mem0, Cognee and Hjarni, checked against their own docs: who writes, what is reviewed, and what each costs.
Share memory and rules across Claude Code, Codex and Cursor
One AGENTS.md covers a repo, and one MCP memory server shares what agents learn. The setup for Claude Code, Cursor and Codex, for you and for a team.
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, at 20% more cost.
Which of my rules did Claude Code actually use?
Claude Code shows which CLAUDE.md and rules files loaded, not which it used. What /context and the InstructionsLoaded hook show, and what served vs cited adds.