Interface reference for people new to Claude's ecosystem
June 2026 · Claude 4 + Fable 5claude_desktop_config.jsonclaude REPL or claude -p pipe mode--model flag or /model command (CLI)path: frontmatter key so they only load when Claude works in matching directories. Ideal for monorepos./memory. Plain markdown; safe to prune..claude/agents/*.md and can be committed./status as "Enterprise managed settings". Individual users cannot override it.@.claude/rules/api.md in a CLAUDE.md imports another file. Useful for organisation — but the imported file still loads at startup and counts toward context. Imports reduce complexity, not token cost./name commands
↗ code.claude.com/docs/en/skills
.claude/skills/) or personal (~/.claude/skills/). Personal skills apply to all your projects.mkdir .claude/skills/pr-prepdescription (used for auto-detection) then markdown instructions below the --- separator./pr-prep, or describe the task and let Claude auto-invoke it when the context matches..claude/, so teammates get them automatically. Treat them as code.`cmd` lines are dynamic context injection — Claude Code runs the shell command and inlines the output into the skill before Claude reads it.
/pr-prep
invocation: explicit in frontmatter. Claude won't auto-run it — you control timing."what changed in my diff?"
invocation or set auto. Claude matches description to context and loads the skill on its own./pr-prep fix auth bug
$ARGUMENTS — reference it inside SKILL.md instructions./skills command to list all loaded skills./init, /compact, /batch plus fully custom commands stored as Markdown in .claude/commands/. Custom commands are unified with Skills: both are invoked as /name; the Skill version takes precedence if both exist.# .claude/commands/pr-prep.md
Run tests, lint, summarise
changes for the PR description.
→ invoke as /pr-prep
SKILL.md file plus supporting assets. Claude auto-detects and applies the skill when the context matches — no manual selection needed. Build once, runs on Claude.ai, Claude Code, and the API unchanged. Stack multiple skills for complex workflows.skills/internal-comms/
SKILL.md # instructions
examples/3p.md # format guides
templates/ # reusable files
"Pull my open Asana tasks
and group by project"
→ Claude calls Asana MCP,
returns live task data
claude_desktop_config.json, or hosted URL-based servers (SSE/HTTP). MCP servers expose tools, resources, and prompts that appear as commands via /mcp__server__prompt.// claude_desktop_config.json
{"mcpServers": {
"github": {
"command": "npx",
"args": ["@mcp/github"]}}}
POST /v1/messages for building Claude-powered products. Now available natively on Claude Platform on AWS with IAM auth. Managed Agents support self-hosted sandboxes (public beta) and private MCP servers — your sandbox, Anthropic's orchestration. Also available via Amazon Bedrock and Google Vertex AI.// agent loop on Anthropic
// tool execution in YOUR infra
providers: ["cloudflare",
"daytona","modal","vercel"]
→ private MCP servers supported
/compact for session compression, prompt caching to cut costs on repeated content, CLAUDE.md for persistent project context, and memory file patterns for agentic loops.system: [{type:"text",
text: "...10k token doc...",
cache_control: {
type:"ephemeral"} }]
→ 90% cost reduction on repeats
thinking blocks, explicit format instructions, positive + negative examples, and task decomposition for complex workflows."Analyse this code.
Reply using:
<issues>...</issues>
<suggestions>...</suggestions>
<severity>low|med|high</severity>"
"You are a senior engineer
on the Payments team. Always
follow our style guide (see
attached docs) and prefer
Stripe SDK over raw HTTP."