Claude Code — Commands
- File format
- Markdown
- Discovery path
-
.claude/commands - Global install path
-
~/.claude/commands - Syllago install method
- Symlink, Direct copy
- Symlink support
- Yes
- Native frontmatter fields
-
name,description,allowed-tools,context,agent,model,disable-model-invocation,user-invocable,argument-hint,effort
Features
How each feature converts to syllago's canonical format. See format conversion for what these statuses mean.
Other features
Behaviors, conventions, and capabilities that aren't tied to a single named field — things like path-based activation, discovery rules, and lifecycle behavior.
| Feature | Conversion | Summary |
|---|---|---|
argument_substitution | Translated Conversion type: Translated Actively mapped to the target provider’s equivalent field during conversion. Learn more → | $ARGUMENTS (all args), $ARGUMENTS[N] (Nth arg), $N (positional), ${CLAUDE_SESSION_ID} and other env vars; shared with skills argument substitution |
builtin_commands | Translated Conversion type: Translated Actively mapped to the target provider’s equivalent field during conversion. Learn more → | 80+ built-in slash commands including /add-dir, /agents, /autofix-pr, /batch [Skill], /branch, /btw, /chrome, /claude-api [Skill], /clear, /color, /compact, /config, /context, /copy, /cost, /debug [Skill], /desktop, /diff, /doctor, /effort, /exit, /export, /extra-usage, /fast, /feedback, /fewer-permission-prompts [Skill], /focus, /heapdump, /help, /hooks, /ide, /init, /insights, /install-github-app, /install-slack-app, /keybindings, /login, /logout, /loop [Skill], /mcp, /memory, /mobile, /model, /passes, /permissions, /plan, /plugin, /powerup, /privacy-settings, /recap, /release-notes, /reload-plugins, /remote-control, /remote-env, /rename, /resume, /review, /rewind, /sandbox, /schedule, /security-review, /setup-bedrock, /setup-vertex, /simplify [Skill], /skills, /stats, /status, /statusline, /stickers, /tasks, /team-onboarding, /teleport, /terminal-setup, /theme, /tui, /ultraplan, /ultrareview, /upgrade, /usage; not user-modifiable; availability varies by platform and plan |
| Command File Format (.md in .claude/commands/) | Translated Conversion type: Translated Actively mapped to the target provider’s equivalent field during conversion. Learn more → | Custom commands are .md files in .claude/commands/ (project) or ~/.claude/commands/ (user); filename becomes the slash command name. These work identically to skills; the skills mechanism is the recommended approach. |
| Command Scopes (project, user) | Translated Conversion type: Translated Actively mapped to the target provider’s equivalent field during conversion. Learn more → | Custom commands live in .claude/commands/ (project) or ~/.claude/commands/ (user); skills take precedence on name collision; symlinks supported. |
| MCP Prompt Commands | Conversion type: No canonical equivalent — appended as prose in a conversion notes block so nothing is silently lost. Learn more → | MCP server prompts appear as /mcp__<servername>__<promptname> slash commands (names normalized; spaces become underscores). Dynamically discovered from connected servers. |
| Built-In Commands | Not portable Conversion type: Not portable Unique to this provider — can’t be carried across providers. Learn more → | 80+ built-in CLI commands covering session management, model/effort control, permissions, MCP, memory, skills, agents, context visualization, git workflows, remote sessions, UI configuration, and more. Availability varies by platform, plan, and environment. |
| Bundled Skill Commands | Not portable Conversion type: Not portable Unique to this provider — can’t be carried across providers. Learn more → | Six commands ship as bundled skills rather than CLI logic (/batch, /claude-api, /debug, /fewer-permission-prompts, /loop, /simplify); use the skill mechanism and appear marked [Skill] in the commands table. |
Sources
| Source |
|---|
| https://code.claude.com/docs/en/commands.md |