The Claude Code Playbook: 2 Updates

Step 1: Log in if you have not already

Step 2: Set workspace trust

Step 3: Start a Remote Control session

Step 4: Connect from your phone

Step 5 (optional): Enable Remote Control for every session automatically

One remote connection per session.

**Terminal must stay open. **

**Laptop must stay on. **

Network timeout.

**You cannot start new sessions remotely. **

**Do not share your session URL or QR code with anyone while the session is active. **

**Your session makes outbound HTTPS requests only. **

Workflow 1: Live Signal to Outreach Intelligence

Workflow 2: Parallel Account Research

Workflow 3: Daily Market Brief on a Schedule

What Stays Available Remotely

Daily Inbox Organisation

Instructions to paste:

"Scan the Inbox folder. Move every file into the relevant document folder based on content type. Create a Markdown report in the Reports folder listing every file moved, where it went, and why."

Frequency: Daily

Daily AI Trend Report

Instructions to paste:

"Search the web and X for the latest news about AI productivity from the past 24 hours relevant to our business. Create a written report with the top findings saved to the Reports folder."

Frequency: Daily

The Team Use Case

The Team Use Case

The Key Principle

The more context Claude has in the folder, the better every scheduled task performs. A CLAUDE.md file with your business, your team, your ICP, and your processes means every task runs with the full picture every single time.

Most people run one Claude session and wait for it to finish before starting the next task. Boris runs 10 to 15 at once.

How to set it up:

• Open 5 terminal tabs. Number them 1 to 5.
• Enable system notifications so Claude pings you when a session needs input
• Open 5 to 10 additional sessions in your browser at claude.ai/code
• Each session handles a different task simultaneously

One researches. One debugs. One builds. You check in when notified.

**Go to claude.ai/code **

**Boris uses Opus 4.5 with thinking for every task. **

This is the most important file. It lives in your project root and Claude reads it at the start of every session.

• The whole team shares one CLAUDE.md checked into git.
• Every time Claude does something wrong, the rule goes in the file so it never happens again.

After every correction, end your message with:

When reviewing a teammate's code, tag @.claude on the pull request to add new rules to CLAUDE.md as part of the review.

Install the Claude Code GitHub action using /install-github-action to enable this.

1. Press Shift and Tab twice at the start of any session to enter Plan Mode.

2. Go back and forth with Claude until the plan is exactly right.

Then switch to auto-accept edits mode and Claude implements it in one go without back and forth.

A good plan is the most important thing.

**If you do something more than once a day, make it a slash command. **

Boris uses /commit-push-pr dozens of times every day. It handles saving, submitting, and opening a review for your code in one command.

Commands live in .claude/commands/ and are checked into git so everyone on your team uses them.

Boris uses three subagents on almost every piece of work:

• code-simplifier: cleans up code after Claude finishes
• verify-app: tests Claude Code end to end before handing back

Install them from the ChernyCode repo included in this resource.

Add a PostToolUse hook that runs your formatter every time Claude edits a file.

Claude generates well-formatted code most of the time. The hook handles the remaining cases before they cause errors later.

Never use --dangerously-skip-permissions.

Claude Code can search and post to Slack, run BigQuery queries for analytics, and pull error logs from Sentry. Check your .mcp.json into git so the whole team gets the same connections.

**For tasks that run a long time, either prompt Claude to verify its work with a background agent when done, use an agent **

Boris says this is the single most important thing.