AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and...
✦ Anthropic
privacy
anthropics/claude-code
Refuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity, and refuses a user-tier plugin's own read of the session's identity.
✦ Anthropic
sec-default
anthropics/claude-code
Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and keeps those plugins from running the model's call before it is allowed; two managed options add a control: allowManagedModsOnly limits mods to the organization's, and forceHotReloadPrompt...
✦ Anthropic
telemetry
anthropics/claude-code
Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.