agentleFS
Sign inStart free
NazmusSayadNazmusSayad/offsite/AGENTS.md

offsite

AGENTS.md9 starsChanged 8 days agoMITView on GitHub

Never alter a provider (Claude Code, Codex, OpenCode) or anything around it: its tools, configuration, sessions, files, or database. Use only what the provider offers through its own CLI, SDK, or API. Never store session history in offsite. The provider owns the history, and offsite reads it from the provider. One exception: search may run rg read-only over Claude Code session files to find candidate sessions. The Claude SDK must confirm every result. Another exception: accounts may read the account…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never run the main offsite instance.

    line 11
  2. Very specific:

    Always use the dialog skill (.claude/skills/dialog/SKILL.md) when adding, changing or reviewing a dialog, alert dialog, popover, hover …

    line 15
  3. Very specific:

    Always start the dev server with pnpm dev from the repository root, unless the user explicitly asks otherwise.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Philosophy

Never alter a provider (Claude Code, Codex, OpenCode) or anything around it: its tools, configuration, sessions, files, or database. Use only what the provider offers through its own CLI, SDK, or API. Never store session history in offsite. The provider owns the history, and offsite reads it from the provider.

One exception: search may run rg read-only over Claude Code session files to find candidate sessions. The Claude SDK must confirm every result.

Another exception: accounts may read the account holder's name, account ID and organization ID read-only, because no provider exposes them: oauthAccount.displayName, oauthAccount.accountUuid and oauthAccount.organizationUuid from Claude Code's .claude.json, and the name, chatgpt_user_id and chatgpt_account_id claims of the ID token in Codex's auth.json. Read nothing else from those files.

Guidelines

Never run the main offsite instance. Never run offsite, npx offsite or pnpm start, and never run the server with the default --dir ~/.offsite. Never stop or restart it either.

Dialogs and Menus

Always use the dialog skill (.claude/skills/dialog/SKILL.md) when adding, changing or reviewing a dialog, alert dialog, popover, hover card, dropdown menu or context menu in the client.

Development

For lint fix and format, use pnpm lint:fix. Do not use prettier.

Always start the dev server with pnpm dev from the repository root, unless the user explicitly asks otherwise.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free