Claude Code Remote
When you want full control an LLM with hands on your files.
Getting Claude Code working takes 30 minutes. Getting it working well takes continuous investment, but that investment compounds.
By the end you will have an AI that knows your standards, follows your voice, and applies your judgment automatically — without typing the same instructions every session.
Machine
*nix machines work best.
- Mac
- Ubuntu Dual Boot
See dev machines for more.
Accounts
AI
Infra
Install
Open VS Code and create a project directory.
Start running a terminal in VS Code.
Install Claude Code:
curl -fsSL https://claude.ai/install.sh | bash
Run:
claude --version
Open Session
Navigate to your project folder in the terminal:
cd /path/to/your/project
claude
You will see the Claude Code prompt. Type anything — ask it to summarize the files in the folder, or just say "hello." This confirms it is working.
What you are looking at: an AI with access to your files. It can read, edit, create, and run commands. Nothing happens without you asking — but it can do a lot when you do.
Write CLAUDE.md
CLAUDE.md is a file at the root of your project. Claude reads it automatically at the start of every session. It is how you teach the AI how you work.
Create the file:
touch CLAUDE.md
Open it and add this minimum viable template:
# Project Instructions
## What This Is
[One sentence describing your project]
## How to Write
- [Your voice or style — e.g. "Short sentences. No jargon."]
- [Any formatting rules — e.g. "Use headers for sections. No bullet soup."]
## What to Avoid
- [Common mistakes you do not want repeated]
- [Any off-limits actions — e.g. "Never delete files without asking."]
## Context
[Two or three sentences about who this work is for and what success looks like]
Fill it in honestly. This file compounds — the clearer it is, the better every session gets.
Creative project (content, marketing, media): focus the "How to Write" section on voice, tone, and what good looks like. "Write like Hemingway. Concrete nouns. Active verbs. No filler." is a valid rule.
Code project: focus on patterns, what frameworks are in use, and what standards to enforce. The Config Architecture guide goes deeper.
Add Rule
Rules are always-loaded constraints — things the AI should never forget. They live in .claude/rules/ and are imported by CLAUDE.md.
Create the first rule:
mkdir -p .claude/rules
Create .claude/rules/voice.md:
# Voice
Write short. Use the active voice. No pleasantries ("Great question!").
No hedging ("It seems like..."). Direct answers only.
Add this line to CLAUDE.md:
@.claude/rules/voice.md
The @ prefix tells Claude to load that file every session. Now the voice rule is always active.
Test it: ask Claude to write a paragraph about the project. If it is still wordy or hedging, tighten the rule. Iteration is fast.
First Skill
A skill is a reusable workflow — a set of instructions Claude follows when invoked with a slash command. Skills turn repeatable work into one-line commands.
Claude Code ships with built-in skills. Try one:
/commit
This skill reads git changes and writes a commit message following best practices. No instructions needed — the skill contains them.
Other built-in skills to explore:
/fix-links— finds and repairs broken internal links/review-pr— reviews a pull request and flags issues
Custom skills are also markdown files. Any instruction you type repeatedly is a candidate. See Skills for how.
Capability Map
Five built-in tool categories form the base of everything Claude Code can do.
| Category | What it does |
|---|---|
| Files | Read, edit, create, rename, reorganize |
| Search | Find by pattern, regex content search, codebase exploration |
| Execution | Shell commands, servers, tests, git |
| Web | Search, fetch docs, look up errors |
| Code intelligence | Type errors, jump to definitions, find references (requires plugins) |
Run Environments
| Environment | Where it runs |
|---|---|
| Local | Your machine — full file, tool, environment access |
| Cloud | Anthropic-managed VMs for offloaded tasks |
| Remote control | Local execution controlled from browser or mobile |
Extend Claude
Five extension types plug into different parts of the loop.
| Extension | What | When it loads |
|---|---|---|
| Skills | Reusable procedures with quality gates | On demand — slash command or auto-match on description |
| MCP | External data sources and APIs | Tool definitions deferred by default |
| Hooks | Shell scripts on lifecycle events | Every matched event — deterministic, not advisory |
| Commands | Single-prompt slash commands | Registered at session start |
| Agent SDK | Custom agents with full orchestration control | Built as separate processes |
Multi-Agent Work
| Pattern | How |
|---|---|
| Sub-agents | Fresh context windows — work doesn't bloat the parent, returns a summary |
| Agent teams | Multiple agents on different parts, lead agent coordinates and merges |
| Orchestrator-workers | Central agent delegates to specialized sub-agents via the Task tool |
Context Primitives
| Primitive | What |
|---|---|
| CLAUDE.md | Project instructions loaded automatically every session |
| Auto memory | Claude saves learnings across sessions — first 200 lines loads per session |
| Auto-compaction | Summarizes older messages when context fills; guided by "Compact Instructions" |
Permission Modes
Toggle with Shift+Tab:
| Mode | Behavior |
|---|---|
| Default | Asks before edits and shell commands |
| Auto-accept edits | Edits files without asking; still asks for other commands |
| Plan mode | Read-only tools only — creates a reviewable plan before execution |
| Auto mode | Background safety checks (research preview) |
Every file edit is snapshotted before changes. Reverse with Esc twice.
Session Control
| Feature | How |
|---|---|
| Resume | claude --continue — same session ID, pick up mid-task |
| Fork | --fork-session — branch a new approach, preserve history |
| Teleport | Pull a web or mobile session into the terminal |
| Worktrees | Parallel sessions on separate branches — see Worktrees |
Workflow Patterns
Five core agentic patterns, each built from different primitives.
| Pattern | Description | Built with |
|---|---|---|
| Prompt chaining | Sequential phases with handoffs between steps | Plan mode + Skills |
| Routing | Different instructions for different contexts or stacks | Conditional CLAUDE.md |
| Parallelization | Independent tasks run simultaneously | Sub-agents |
| Orchestrator-workers | Central agent delegates to specialists | Task tool |
| Evaluator-optimizer | Output validated inside the same loop | Inline skills |
Integration Points
| Surface | Entry |
|---|---|
| Terminal | claude CLI command |
| IDE | VS Code and JetBrains plugins |
| Scheduled | Cloud tasks (Anthropic infra), desktop scheduler, /loop in-session |
| Channels | Telegram, Discord, iMessage webhooks |
| CI/CD | GitHub Actions, GitLab CI/CD |
| Browser | Chrome extension |
The Loop
Three phases blend continuously:
Gather context → Take action → Verify results
Context management — CLAUDE.md, memory, auto-compaction — determines how far the loop runs before it degrades. The harness (tools + context + execution environment) turns the model into an agent.
Cascade Starts
You now have:
- A
CLAUDE.mdthat orients every session - A rule that enforces your voice
- Skills you can invoke for repeatable work
That is the beginning of the Cascade:
Mantra (your intention)
→ Rule (always enforced)
→ Hook (runs automatically on every action)
→ System (you never think about it again)
You are at Rule. The next step — hooks — are shell scripts that run when Claude takes certain actions. They are optional but powerful: a hook can automatically check that every file Claude edits passes a quality test.
The pattern compounds. The longer the loop runs, the more it learns your judgment. The more it learns your judgment, the less you explain.
What Next
| To... | Go to |
|---|---|
| Climb to Step 3 of the ladder | Hermes Onboarding |
| Understand the full config architecture | Config Architecture |
| Build your own skills | Skills |
| Use subagents for parallel work | Agents |
| Choose the right AI model | LLM Comparison |
| See the Cascade concept in full | Mantra |
Context
- Onboarding Ladder — the three-step journey from ask to orchestrate
- Perplexity — Step 1, zero-setup browser entry
- Hermes Onboarding — Step 3, autonomous orchestration
- Config Architecture — structure your config so it works with any AI tool
- Mantra — the Cascade under every productive AI setup
- Standards — the AAIF standard governing skills and agent config
Links
- Agentic Workflow Patterns — MindStudio breakdown of orchestration patterns
- Five Agentic Patterns — practical pattern guide with Claude Code examples
- Agentic Coding Principles — session management, auto-compaction, and safe agentic loops
Questions
What would have to be true about your CLAUDE.md for Claude to be genuinely useful after one session, without any additional instruction?
- Which repeatable workflow would save the most time as a single slash command?
- If the Cascade fully runs — Mantra → Rule → Hook → System — what does your work look like differently in six months?
- Where does your judgment matter most today, and is that where the AI should learn first?