# Config Guide

> Reference guide for configuring @Claude agents — agents, agent scopes, identity profiles, presets, connections, rules, GitHub repositories, and custom instructions. Explains the inheritance model and configuration best practices.

- Skill: `anthropics/config-guide` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add anthropics/config-guide`
- Raw SKILL.md: https://api.skillmd.com/api/skills/anthropics/config-guide/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: anthropics (https://skillmd.com/u/anthropics)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/anthropics/config-guide

---


# @Claude — Configuration Guide

@Claude is configured through a small set of layered objects in the claude.ai
admin settings: **agents**, **agent scopes**, **identity profiles**, and the
**presets / connections / repos / instructions** attached to them. The
layering decides what any given session can see and do.

This guide is currently written for the **Slack** surface.

This skill is an **index**. Read the relevant reference file below for the
topic the user is asking about — each is short and self-contained.

| Topic | Reference file |
|---|---|
| Agents, agent scopes, the resolution chain, and per-field inheritance | `agents-and-scopes.md` |
| Identity profiles, scopes, rules, credentials, repo permissions | `identity-profiles.md` |
| Presets, connections (OAuth / MCP), how to install one | `connections-and-presets.md` |
| GitHub repositories and custom instructions | `github-and-instructions.md` |
| Best practices: profile layout, read-only vs read/write, rollout | `best-practices.md` |

All reference files live alongside this `SKILL.md` in the same directory.

After explaining configuration, you can suggest the user run the
`debug-plugins` skill in a **new** Slack thread to confirm the change actually
took effect inside the container.